thoth-agent

name	thoth-agent
description	Configure, extend, or contribute to Thoth Agent.
version	2.1.0
author	Thoth Agent + Teknium
license	MIT
platforms	["linux","macos","windows"]
metadata	{"thoth":{"tags":["thoth","setup","configuration","multi-agent","spawning","cli","gateway","development"],"homepage":"https://github.com/519lab/thoth-agent","related_skills":["claude-code","codex","opencode","substrate"]}}

Thoth Agent

Thoth Agent is an open-source AI agent framework (a fork of Hermes by Nous Research) that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Thoth works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL.

What makes Thoth different:

• Self-improving through skills — Thoth learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment.
• Persistent memory across sessions — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works.
• Multi-platform gateway — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat.
• Provider-agnostic — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.
• Profiles — run multiple independent Thoth instances with isolated configs, sessions, skills, and memory.
• Extensible — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.

People use Thoth for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access.

This skill helps you work with Thoth Agent effectively — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it.

Docs: https://thoth.519lab.com/docs/

Quick Start

# Install
curl -fsSL https://raw.githubusercontent.com/519lab/thoth-agent/main/scripts/install.sh | bash

# Interactive chat (default)
thoth

# Single query
thoth chat -q "What is the capital of France?"

# Setup wizard
thoth setup

# Change model/provider
thoth model

# Check health
thoth doctor

---

CLI Reference

Global Flags

thoth [flags] [command]

  --version, -V             Show version
  --resume, -r SESSION      Resume session by ID or title
  --continue, -c [NAME]     Resume by name, or most recent session
  --worktree, -w            Isolated git worktree mode (parallel agents)
  --skills, -s SKILL        Preload skills (comma-separate or repeat)
  --profile, -p NAME        Use a named profile
  --yolo                    Skip dangerous command approval
  --pass-session-id         Include session ID in system prompt

No subcommand defaults to chat.

Chat

thoth chat [flags]
  -q, --query TEXT          Single query, non-interactive
  -m, --model MODEL         Model (e.g. anthropic/claude-sonnet-4)
  -t, --toolsets LIST       Comma-separated toolsets
  --provider PROVIDER       Force provider (openrouter, anthropic, nous, etc.)
  -v, --verbose             Verbose output
  -Q, --quiet               Suppress banner, spinner, tool previews
  --checkpoints             Enable filesystem checkpoints (/rollback)
  --source TAG              Session source tag (default: cli)

Configuration

thoth setup [section]      Interactive wizard (model|terminal|gateway|tools|agent)
thoth model                Interactive model/provider picker
thoth config               View current config
thoth config edit          Open config.yaml in $EDITOR
thoth config set KEY VAL   Set a config value
thoth config path          Print config.yaml path
thoth config env-path      Print .env path
thoth config check         Check for missing/outdated config
thoth config migrate       Update config with new options
thoth login [--provider P] OAuth login (nous, openai-codex)
thoth logout               Clear stored auth
thoth doctor [--fix]       Check dependencies and config
thoth status [--all]       Show component status

Tools & Skills

thoth tools                Interactive tool enable/disable (curses UI)
thoth tools list           Show all tools and status
thoth tools enable NAME    Enable a toolset
thoth tools disable NAME   Disable a toolset

thoth skills list          List installed skills
thoth skills search QUERY  Search the skills hub
thoth skills install ID    Install a skill (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name)
thoth skills inspect ID    Preview without installing
thoth skills config        Enable/disable skills per platform
thoth skills check         Check for updates
thoth skills update        Update outdated skills
thoth skills uninstall N   Remove a hub skill
thoth skills publish PATH  Publish to registry
thoth skills browse        Browse all available skills
thoth skills tap add REPO  Add a GitHub repo as skill source

MCP Servers

thoth mcp serve            Run Thoth as an MCP server
thoth mcp add NAME         Add an MCP server (--url or --command)
thoth mcp remove NAME      Remove an MCP server
thoth mcp list             List configured servers
thoth mcp test NAME        Test connection
thoth mcp configure NAME   Toggle tool selection

Gateway (Messaging Platforms)

thoth gateway run          Start gateway foreground
thoth gateway install      Install as background service
thoth gateway start/stop   Control the service
thoth gateway restart      Restart the service
thoth gateway status       Check status
thoth gateway setup        Configure platforms

Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, BlueBubbles (iMessage), API Server, Webhooks. Open WebUI connects via the API Server adapter.

Platform docs: https://thoth.519lab.com/docs/user-guide/messaging/

Sessions

thoth sessions list        List recent sessions
thoth sessions browse      Interactive picker
thoth sessions export OUT  Export to JSONL
thoth sessions rename ID T Rename a session
thoth sessions delete ID   Delete a session
thoth sessions prune       Clean up old sessions (--older-than N days)
thoth sessions stats       Session store statistics

Cron Jobs

thoth cron list            List jobs (--all for disabled)
thoth cron create SCHED    Create: '30m', 'every 2h', '0 9 * * *'
thoth cron edit ID         Edit schedule, prompt, delivery
thoth cron pause/resume ID Control job state
thoth cron run ID          Trigger on next tick
thoth cron remove ID       Delete a job
thoth cron status          Scheduler status

Webhooks

thoth webhook subscribe N  Create route at /webhooks/<name>
thoth webhook list         List subscriptions
thoth webhook remove NAME  Remove a subscription
thoth webhook test NAME    Send a test POST

Profiles

thoth profile list         List all profiles
thoth profile create NAME  Create (--clone, --clone-all, --clone-from)
thoth profile use NAME     Set sticky default
thoth profile delete NAME  Delete a profile
thoth profile show NAME    Show details
thoth profile alias NAME   Manage wrapper scripts
thoth profile rename A B   Rename a profile
thoth profile export NAME  Export to tar.gz
thoth profile import FILE  Import from archive

Credential Pools

thoth auth add             Interactive credential wizard
thoth auth list [PROVIDER] List pooled credentials
thoth auth remove P INDEX  Remove by provider + index
thoth auth reset PROVIDER  Clear exhaustion status

Other

thoth insights [--days N]  Usage analytics
thoth update               Update to latest version
thoth pairing list/approve/revoke  DM authorization
thoth plugins list/install/remove  Plugin management
thoth honcho setup/status  Honcho memory integration (requires honcho plugin)
thoth memory setup/status/off  Memory provider config
thoth completion bash|zsh  Shell completions
thoth acp                  ACP server (IDE integration)
thoth claw migrate         Migrate from OpenClaw
thoth uninstall            Uninstall Thoth

---

Slash Commands (In-Session)

Type these during an interactive chat session. New commands land fairly often; if something below looks stale, run /help in-session for the authoritative list or see the live slash commands reference. The registry of record is thoth_cli/commands.py — every consumer (autocomplete, Telegram menu, Slack mapping, /help) derives from it.

Session Control

/new (/reset)        Fresh session
/clear               Clear screen + new session (CLI)
/retry               Resend last message
/undo                Remove last exchange
/title [name]        Name the session
/compress            Manually compress context
/stop                Kill background processes
/rollback [N]        Restore filesystem checkpoint
/snapshot [sub]      Create or restore state snapshots of Thoth config/state (CLI)
/background <prompt> Run prompt in background
/queue <prompt>      Queue for next turn
/steer <prompt>      Inject a message after the next tool call without interrupting
/agents (/tasks)     Show active agents and running tasks
/resume [name]       Resume a named session
/goal [text|sub]     Set a standing goal Thoth works on across turns until achieved
                     (subcommands: status, pause, resume, clear)
/redraw              Force a full UI repaint (CLI)

Configuration

/config              Show config (CLI)
/model [name]        Show or change model
/personality [name]  Set personality
/reasoning [level]   Set reasoning (none|minimal|low|medium|high|xhigh|show|hide)
/verbose             Cycle: off → new → all → verbose
/voice [on|off|tts]  Voice mode
/yolo                Toggle approval bypass
/busy [sub]          Control what Enter does while Thoth is working (CLI)
                     (subcommands: queue, steer, interrupt, status)
/indicator [style]   Pick the TUI busy-indicator style (CLI)
                     (styles: kaomoji, emoji, unicode, ascii)
/footer [on|off]     Toggle gateway runtime-metadata footer on final replies
/skin [name]         Change theme (CLI)
/statusbar           Toggle status bar (CLI)

Tools & Skills

/tools               Manage tools (CLI)
/toolsets            List toolsets (CLI)
/skills              Search/install skills (CLI)
/skill <name>        Load a skill into session
/reload-skills       Re-scan ~/.thoth/skills/ for added/removed skills
/reload              Reload .env variables into the running session (CLI)
/reload-mcp          Reload MCP servers
/cron                Manage cron jobs (CLI)
/curator [sub]       Background skill maintenance (status, run, pin, archive, …)
/kanban [sub]        Multi-profile collaboration board (tasks, links, comments)
/plugins             List plugins (CLI)

Gateway

/approve             Approve a pending command (gateway)
/deny                Deny a pending command (gateway)
/restart             Restart gateway (gateway)
/sethome             Set current chat as home channel (gateway)
/update              Update Thoth to latest (gateway)
/topic [sub]         Enable or inspect Telegram DM topic sessions (gateway)
/platforms (/gateway) Show platform connection status (gateway)

Utility

/branch (/fork)      Branch the current session
/fast                Toggle priority/fast processing
/browser             Open CDP browser connection
/history             Show conversation history (CLI)
/save                Save conversation to file (CLI)
/copy [N]            Copy the last assistant response to clipboard (CLI)
/paste               Attach clipboard image (CLI)
/image               Attach local image file (CLI)

Info

/help                Show commands
/commands [page]     Browse all commands (gateway)
/usage               Token usage
/insights [days]     Usage analytics
/gquota              Show Google Gemini Code Assist quota usage (CLI)
/status              Session info (gateway)
/profile             Active profile info
/debug               Upload debug report (system info + logs) and get shareable links

Exit

/quit (/exit, /q)    Exit CLI

---

Key Paths & Config

~/.thoth/config.yaml        Main configuration
~/.thoth/.env               API keys and secrets
$THOTH_HOME/skills/        Installed skills
~/.thoth/sessions/          Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true)
~/.thoth/logs/              Gateway and error logs
~/.thoth/auth.json          OAuth tokens and credential pools
~/.thoth/thoth-agent/       Source code (if git-installed)

Substrate Edition (this fork) differences: session + kanban + substrate state all live in PostgreSQL (DSN THOTH_PG_DSN; default postgresql://thoth:thoth@localhost:5432/thoth) rather than state.db. The state.db SQLite file no longer exists in this fork. The installer's defaults place THOTH_HOME at ~/.thoth/ and the launcher at thoth; pass --cli-name thoth-substrate --thoth-home ~/.thoth-substrate to coexist with an existing upstream install.

Profiles use ~/.thoth/profiles/<name>/ with the same layout.

Config Sections

Edit with thoth config edit or thoth config set section.key value.

Section	Key options
model	default, provider, base_url, api_key, context_length
agent	max_turns (90), tool_use_enforcement
terminal	backend (local/docker/ssh/modal), cwd, timeout (180)
compression	enabled, threshold (0.50), target_ratio (0.20)
display	skin, tool_progress, show_reasoning, show_cost
stt	enabled, provider (local/groq/openai/mistral)
tts	provider (edge/elevenlabs/openai/minimax/mistral/neutts)
memory	memory_enabled, user_profile_enabled, provider
security	tirith_enabled, website_blocklist
delegation	model, provider, base_url, api_key, max_iterations (50), reasoning_effort
checkpoints	enabled, max_snapshots (50)

Full config reference: https://thoth.519lab.com/docs/user-guide/configuration

Providers

20+ providers supported. Set via thoth model or thoth setup.

Provider	Auth	Key env var
OpenRouter	API key	OPENROUTER_API_KEY
Anthropic	API key	ANTHROPIC_API_KEY
Nous Portal	OAuth	thoth auth
OpenAI Codex	OAuth	thoth auth
GitHub Copilot	Token	COPILOT_GITHUB_TOKEN
Google Gemini	API key	GOOGLE_API_KEY or GEMINI_API_KEY
DeepSeek	API key	DEEPSEEK_API_KEY
xAI / Grok	API key	XAI_API_KEY
Hugging Face	Token	HF_TOKEN
Z.AI / GLM	API key	GLM_API_KEY
MiniMax	API key	MINIMAX_API_KEY
MiniMax CN	API key	MINIMAX_CN_API_KEY
Kimi / Moonshot	API key	KIMI_API_KEY
Alibaba / DashScope	API key	DASHSCOPE_API_KEY
Xiaomi MiMo	API key	XIAOMI_API_KEY
Kilo Code	API key	KILOCODE_API_KEY
AI Gateway (Vercel)	API key	AI_GATEWAY_API_KEY
OpenCode Zen	API key	OPENCODE_ZEN_API_KEY
OpenCode Go	API key	OPENCODE_GO_API_KEY
Qwen OAuth	OAuth	thoth login --provider qwen-oauth
Custom endpoint	Config	model.base_url + model.api_key in config.yaml
GitHub Copilot ACP	External	COPILOT_CLI_PATH or Copilot CLI

Full provider docs: https://thoth.519lab.com/docs/integrations/providers

Toolsets

Enable/disable via thoth tools (interactive) or thoth tools enable/disable NAME.

Toolset	What it provides
web	Web search and content extraction
search	Web search only (subset of web)
browser	Browser automation (Browserbase, Camofox, or local Chromium)
terminal	Shell commands and process management
file	File read/write/search/patch
code_execution	Sandboxed Python execution
vision	Image analysis
image_gen	AI image generation
video	Video analysis and generation
tts	Text-to-speech
skills	Skill browsing and management
memory	Persistent cross-session memory
session_search	Search past conversations
delegation	Subagent task delegation
cronjob	Scheduled task management
clarify	Ask user clarifying questions
messaging	Cross-platform message sending
todo	In-session task planning and tracking
kanban	Multi-agent work-queue tools (gated to workers)
debugging	Extra introspection/debug tools (off by default)
safe	Minimal, low-risk toolset for locked-down sessions
spotify	Spotify playback and playlist control
homeassistant	Smart home control (off by default)
discord	Discord integration tools
discord_admin	Discord admin/moderation tools
rl	Reinforcement learning tools (off by default)
moa	Mixture of Agents (off by default)

Full enumeration lives in toolsets.py as the TOOLSETS dict; _THOTH_CORE_TOOLS is the default bundle most platforms inherit from.

Tool changes take effect on /reset (new session). They do NOT apply mid-conversation to preserve prompt caching.

---

Security & Privacy Toggles

Common "why is Thoth doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (/reset in chat, or start a new thoth invocation) because they're read once at startup.

Secret redaction in tool output

Secret redaction is off by default — tool output (terminal stdout, read_file, web content, subagent summaries, etc.) passes through unmodified. If the user wants Thoth to auto-mask strings that look like API keys, tokens, and secrets before they enter the conversation context and logs:

thoth config set security.redact_secrets true       # enable globally

Restart required. security.redact_secrets is snapshotted at import time — toggling it mid-session (e.g. via export THOTH_REDACT_SECRETS=true from a tool call) will NOT take effect for the running process. Tell the user to run thoth config set security.redact_secrets true in a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task.

Disable again with:

thoth config set security.redact_secrets false

PII redaction in gateway messages

Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model:

thoth config set privacy.redact_pii true    # enable
thoth config set privacy.redact_pii false   # disable (default)

Command approval prompts

By default (approvals.mode: manual), Thoth prompts the user before running shell commands flagged as destructive (rm -rf, git reset --hard, etc.). The modes are:

• manual — always prompt (default)
• smart — use an auxiliary LLM to auto-approve low-risk commands, prompt on high-risk
• off — skip all approval prompts (equivalent to --yolo)

thoth config set approvals.mode smart       # recommended middle ground
thoth config set approvals.mode off         # bypass everything (not recommended)

Per-invocation bypass without changing config:

• thoth --yolo …
• export THOTH_YOLO_MODE=1

Note: YOLO / approvals.mode: off does NOT turn off secret redaction. They are independent.

Shell hooks allowlist

Some shell-hook integrations require explicit allowlisting before they fire. Managed via ~/.thoth/shell-hooks-allowlist.json — prompted interactively the first time a hook wants to run.

Disabling the web/browser/image-gen tools

To keep the model away from network or media tools entirely, open thoth tools and toggle per-platform. Takes effect on next session (/reset). See the Tools & Skills section above.

---

Voice & Transcription

STT (Voice → Text)

Voice messages from messaging platforms are auto-transcribed.

Provider priority (auto-detected):

1. Local faster-whisper — free, no API key: pip install faster-whisper
2. Groq Whisper — free tier: set GROQ_API_KEY
3. OpenAI Whisper — paid: set VOICE_TOOLS_OPENAI_KEY
4. Mistral Voxtral — set MISTRAL_API_KEY

Config:

stt:
  enabled: true
  provider: local        # local, groq, openai, mistral
  local:
    model: base          # tiny, base, small, medium, large-v3

TTS (Text → Voice)

Provider	Env var	Free?
Edge TTS	None	Yes (default)
ElevenLabs	ELEVENLABS_API_KEY	Free tier
OpenAI	VOICE_TOOLS_OPENAI_KEY	Paid
MiniMax	MINIMAX_API_KEY	Paid
Mistral (Voxtral)	MISTRAL_API_KEY	Paid
NeuTTS (local)	None (pip install neutts[all] + espeak-ng)	Free

Voice commands: /voice on (voice-to-voice), /voice tts (always voice), /voice off.

---

Spawning Additional Thoth Instances

Run additional Thoth processes as fully independent subprocesses — separate sessions, tools, and environments.

When to Use This vs delegate_task

	delegate_task	Spawning thoth process
Isolation	Separate conversation, shared process	Fully independent process
Duration	Minutes (bounded by parent loop)	Hours/days
Tool access	Subset of parent's tools	Full tool access
Interactive	No	Yes (PTY mode)
Use case	Quick parallel subtasks	Long autonomous missions

One-Shot Mode

terminal(command="thoth chat -q 'Research GRPO papers and write summary to ~/research/grpo.md'", timeout=300)

# Background for long tasks:
terminal(command="thoth chat -q 'Set up CI/CD for ~/myapp'", background=true)

Interactive PTY Mode (via tmux)

Thoth uses prompt_toolkit, which requires a real terminal. Use tmux for interactive spawning:

# Start
terminal(command="tmux new-session -d -s agent1 -x 120 -y 40 'thoth'", timeout=10)

# Wait for startup, then send a message
terminal(command="sleep 8 && tmux send-keys -t agent1 'Build a FastAPI auth service' Enter", timeout=15)

# Read output
terminal(command="sleep 20 && tmux capture-pane -t agent1 -p", timeout=5)

# Send follow-up
terminal(command="tmux send-keys -t agent1 'Add rate limiting middleware' Enter", timeout=5)

# Exit
terminal(command="tmux send-keys -t agent1 '/exit' Enter && sleep 2 && tmux kill-session -t agent1", timeout=10)

Multi-Agent Coordination

# Agent A: backend
terminal(command="tmux new-session -d -s backend -x 120 -y 40 'thoth -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t backend 'Build REST API for user management' Enter", timeout=15)

# Agent B: frontend
terminal(command="tmux new-session -d -s frontend -x 120 -y 40 'thoth -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t frontend 'Build React dashboard for user management' Enter", timeout=15)

# Check progress, relay context between them
terminal(command="tmux capture-pane -t backend -p | tail -30", timeout=5)
terminal(command="tmux send-keys -t frontend 'Here is the API schema from the backend agent: ...' Enter", timeout=5)

Session Resume

# Resume most recent session
terminal(command="tmux new-session -d -s resumed 'thoth --continue'", timeout=10)

# Resume specific session
terminal(command="tmux new-session -d -s resumed 'thoth --resume 20260225_143052_a1b2c3'", timeout=10)

Tips

• Prefer delegate_task for quick subtasks — less overhead than spawning a full process
• Use -w (worktree mode) when spawning agents that edit code — prevents git conflicts
• Set timeouts for one-shot mode — complex tasks can take 5-10 minutes
• Use thoth chat -q for fire-and-forget — no PTY needed
• Use tmux for interactive sessions — raw PTY mode has \r vs \n issues with prompt_toolkit
• For scheduled tasks, use the cronjob tool instead of spawning — handles delivery and retry

---

Durable & Background Systems

Four systems run alongside the main conversation loop. Quick reference here; full developer notes live in CLAUDE.md, user-facing docs under website/docs/user-guide/features/.

Delegation (delegate_task)

Synchronous subagent spawn — the parent waits for the child's summary before continuing its own loop. Isolated context + terminal session.

• Single: delegate_task(goal, context, toolsets).
• Batch: delegate_task(tasks=[{goal, ...}, ...]) runs children in parallel, capped by delegation.max_concurrent_children (default 3).
• Roles: leaf (default; cannot re-delegate) vs orchestrator (can spawn its own workers, bounded by delegation.max_spawn_depth).
• Not durable. If the parent is interrupted, the child is cancelled. For work that must outlive the turn, use cronjob or terminal(background=True, notify_on_complete=True).

Config: delegation.* in config.yaml.

Cron (scheduled jobs)

Durable scheduler — cron/jobs.py + cron/scheduler.py. Drive it via the cronjob tool, the thoth cron CLI (list, add, edit, pause, resume, run, remove), or the /cron slash command.

• Schedules: duration ("30m", "2h"), "every" phrase ("every monday 9am"), 5-field cron ("0 9 * * *"), or ISO timestamp.
• Per-job knobs: skills, model/provider override, script (pre-run data collection; no_agent=True makes the script the whole job), context_from (chain job A's output into job B), workdir (run in a specific dir with its AGENTS.md / CLAUDE.md loaded), multi-platform delivery.
• Invariants: 3-minute hard interrupt per run, .tick.lock file prevents duplicate ticks across processes, cron sessions pass skip_memory=True by default, and cron deliveries are framed with a header/footer instead of being mirrored into the target gateway session (keeps role alternation intact).

User docs: https://thoth.519lab.com/docs/user-guide/features/cron

Curator (skill lifecycle)

Background maintenance for agent-created skills. Tracks usage, marks idle skills stale, archives stale ones, keeps a pre-run tar.gz backup so nothing is lost.

• CLI: thoth curator <verb> — status, run, pause, resume, pin, unpin, archive, restore, prune, backup, rollback.
• Slash: /curator <subcommand> mirrors the CLI.
• Scope: only touches skills with created_by: "agent" provenance. Bundled + hub-installed skills are off-limits. Never deletes — max destructive action is archive. Pinned skills are exempt from every auto-transition and every LLM review pass.
• Telemetry: sidecar at ~/.thoth/skills/.usage.json holds per-skill use_count, view_count, patch_count, last_activity_at, state, pinned.

Config: curator.* (enabled, interval_hours, min_idle_hours, stale_after_days, archive_after_days, backup.*). User docs: https://thoth.519lab.com/docs/user-guide/features/curator

Kanban (multi-agent work queue)

Durable SQLite board for multi-profile / multi-worker collaboration. Users drive it via thoth kanban <verb>; dispatcher-spawned workers see a focused kanban_* toolset gated by THOTH_KANBAN_TASK, and orchestrator profiles can opt into the broader kanban toolset. Normal sessions still have zero kanban_* schema footprint unless configured.

• CLI verbs (common): init, create, list (alias ls), show, assign, link, unlink, comment, complete, block, unblock, archive, tail. Less common: watch, stats, runs, log, dispatch, daemon, gc.
• Worker/orchestrator toolset: kanban_show, kanban_complete, kanban_block, kanban_heartbeat, kanban_comment, kanban_create, kanban_link; profiles that explicitly enable the kanban toolset outside a dispatcher-spawned task also get kanban_list and kanban_unblock for board routing.
• Dispatcher runs inside the gateway by default (kanban.dispatch_in_gateway: true) — reclaims stale claims, promotes ready tasks, atomically claims, spawns assigned profiles. Auto-blocks a task after failure_limit consecutive spawn failures (default 2; configurable via kanban.failure_limit or per-task max_retries).
• Isolation: board is the hard boundary (workers get THOTH_KANBAN_BOARD pinned in env); tenant is a soft namespace within a board for workspace-path + memory-key isolation.

User docs: https://thoth.519lab.com/docs/user-guide/features/kanban

Cognitive Substrate (this fork only)

Substrate Edition (519lab/thoth-agent) adds a PostgreSQL-backed perception/memory layer that runs alongside the conversation loop. The substrate is additional infrastructure — persistent memory, skills, session search, and Honcho all keep working exactly as upstream describes; the substrate sits underneath them as a unified perception sink + recall source. Upstream Hermes does not have this layer.

What runs in the background:

• Sentinel — polls the pending slice queue (200 ms tick), decides pass/quarantine on every incoming slice. Phase A stub passes everything through; real defense (prompt-injection, content poisoning) lands later.
• Curator — continuous decay + release loop. Slices fade per their decay profile's half-life, get released below threshold per the profile's tombstone policy, and Curator backfills semantic embeddings (text-embedding-3-small, 1536-d) for unembedded passed slices in batches so recall has full vector coverage over time.
• Force-reject — 10 s tick that drops pending slices past their decay-profile TTL so the pending queue stays bounded even if Sentinel falls behind.
• Partition-maintenance — 24 h tick that keeps a rolling window of 3 monthly partitions ahead of now() on substrate_slices.

Perception emission is wired into every user message, assistant response, tool call/result, sub-agent spawn/return, session-lifecycle event, and cron dispatch — each lands as a slice on a named stream (e.g. thoth.world.user_message.cli, thoth.self_action.assistant_response). Slice writes are non-fatal: substrate failures never break the foreground conversation.

Recall API + memory-context (Phase C, env-gated): when THOTH_SUBSTRATE_RECALL=1 is set, a SubstrateMemoryProvider is registered into Thoth's MemoryManager and the per-turn <memory-context> block is composed from substrate slices (composite score = pgvector similarity + keyword Jaccard + salience + recency, ranked under a token budget). Default is 0 — registration is exercised but prefetch() returns "" and the upstream memory path stays authoritative. The model also gets a substrate_recall_more tool when the provider is active for explicit deeper-search asks.

Introspect:

thoth substrate            # streams + slice counts + pending queue
thoth substrate streams    # per-stream counts
thoth substrate curator    # decay/release activity
thoth substrate recall     # recall coverage + recent calls

Deeper operator workflow lives in the substrate bundled skill — load it with /substrate or thoth -s substrate.

---

Windows-Specific Quirks

Thoth runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash mintty, VS Code integrated terminal). Most of it just works, but a handful of differences between Win32 and POSIX have bitten us — document new ones here as you hit them so the next person (or the next session) doesn't rediscover them from scratch.

Input / Keybindings

Alt+Enter doesn't insert a newline. Windows Terminal intercepts Alt+Enter at the terminal layer to toggle fullscreen — the keystroke never reaches prompt_toolkit. Use Ctrl+Enter instead. Windows Terminal delivers Ctrl+Enter as LF (c-j), distinct from plain Enter (c-m / CR), and the CLI binds c-j to newline insertion on win32 only (see _bind_prompt_submit_keys + the Windows-only c-j binding in cli.py). Side effect: the raw Ctrl+J keystroke also inserts a newline on Windows — unavoidable, because Windows Terminal collapses Ctrl+Enter and Ctrl+J to the same keycode at the Win32 console API layer. No conflicting binding existed for Ctrl+J on Windows, so this is a harmless side effect.

mintty / git-bash behaves the same (fullscreen on Alt+Enter) unless you disable Alt+Fn shortcuts in Options → Keys. Easier to just use Ctrl+Enter.

Diagnosing keybindings. Run python scripts/keystroke_diagnostic.py (repo root) to see exactly how prompt_toolkit identifies each keystroke in the current terminal. Answers questions like "does Shift+Enter come through as a distinct key?" (almost never — most terminals collapse it to plain Enter) or "what byte sequence is my terminal sending for Ctrl+Enter?" This is how the Ctrl+Enter = c-j fact was established.

Config / Files

HTTP 400 "No models provided" on first run. config.yaml was saved with a UTF-8 BOM (common when Windows apps write it). Re-save as UTF-8 without BOM. thoth config edit writes without BOM; manual edits in Notepad are the usual culprit.

execute_code / Sandbox

WinError 10106 ("The requested service provider could not be loaded or initialized") from the sandbox child process — it can't create an AF_INET socket, so the loopback-TCP RPC fallback fails before connect(). Root cause is usually not a broken Winsock LSP; it's Thoth's own env scrubber dropping SYSTEMROOT / WINDIR / COMSPEC from the child env. Python's socket module needs SYSTEMROOT to locate mswsock.dll. Fixed via the _WINDOWS_ESSENTIAL_ENV_VARS allowlist in tools/code_execution_tool.py. If you still hit it, echo os.environ inside an execute_code block to confirm SYSTEMROOT is set. Full diagnostic recipe in references/execute-code-sandbox-env-windows.md.

Testing / Contributing

scripts/run_tests.sh doesn't work as-is on Windows — it looks for POSIX venv layouts (.venv/bin/activate). The Thoth-installed venv at venv/Scripts/ has no pip or pytest either (stripped for install size). Workaround: install pytest + pytest-xdist + pyyaml into a system Python 3.11 user site, then invoke pytest directly with PYTHONPATH set:

"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml
export PYTHONPATH="$(pwd)"
"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0

Use -n 0, not -n 4 — pyproject.toml's default addopts already includes -n, and the wrapper's CI-parity guarantees don't apply off POSIX.

POSIX-only tests need skip guards. Common markers already in the codebase:

• Symlinks — elevated privileges on Windows
• 0o600 file modes — POSIX mode bits not enforced on NTFS by default
• signal.SIGALRM — Unix-only (see tests/conftest.py::_enforce_test_timeout)
• Winsock / Windows-specific regressions — @pytest.mark.skipif(sys.platform != "win32", ...)

Use the existing skip-pattern style (sys.platform == "win32" or sys.platform.startswith("win")) to stay consistent with the rest of the suite.

Path / Filesystem

Line endings. Git may warn LF will be replaced by CRLF the next time Git touches it. Cosmetic — the repo's .gitattributes normalizes. Don't let editors auto-convert committed POSIX-newline files to CRLF.

Forward slashes work almost everywhere. C:/Users/... is accepted by every Thoth tool and most Windows APIs. Prefer forward slashes in code and logs — avoids shell-escaping backslashes in bash.

---

Troubleshooting

Voice not working

1. Check stt.enabled: true in config.yaml
2. Verify provider: pip install faster-whisper or set API key
3. In gateway: /restart. In CLI: exit and relaunch.

Tool not available

1. thoth tools — check if toolset is enabled for your platform
2. Some tools need env vars (check .env)
3. /reset after enabling tools

Model/provider issues

1. thoth doctor — check config and dependencies
2. thoth login — re-authenticate OAuth providers
3. Check .env has the right API key
4. Copilot 403: gh auth login tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via thoth model → GitHub Copilot.

Changes not taking effect

• Tools/skills: /reset starts a new session with updated toolset
• Config changes: In gateway: /restart. In CLI: exit and relaunch.
• Code changes: Restart the CLI or gateway process

Skills not showing

1. thoth skills list — verify installed
2. thoth skills config — check platform enablement
3. Load explicitly: /skill name or thoth -s name

Gateway issues

Check logs first:

grep -i "failed to send\|error" ~/.thoth/logs/gateway.log | tail -20

Common gateway problems:

• Gateway dies on SSH logout: Enable linger: sudo loginctl enable-linger $USER
• Gateway dies on WSL2 close: WSL2 requires systemd=true in /etc/wsl.conf for systemd services to work. Without it, gateway falls back to nohup (dies when session closes).
• Gateway crash loop: Reset the failed state: systemctl --user reset-failed thoth-gateway

Platform-specific issues

• Discord bot silent: Must enable Message Content Intent in Bot → Privileged Gateway Intents.
• Slack bot only works in DMs: Must subscribe to message.channels event. Without it, the bot ignores public channels.
• Windows-specific issues (Alt+Enter newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated Windows-Specific Quirks section above.

Auxiliary models not working

If auxiliary tasks (vision, compression, session_search) fail silently, the auto provider can't find a backend. Either set OPENROUTER_API_KEY or GOOGLE_API_KEY, or explicitly configure each auxiliary task's provider:

thoth config set auxiliary.vision.provider <your_provider>
thoth config set auxiliary.vision.model <model_name>

---

Where to Find Things

Looking for...	Location
Config options	thoth config edit or Configuration docs
Available tools	thoth tools list or Tools reference
Slash commands	/help in session or Slash commands reference
Skills catalog	thoth skills browse or Skills catalog
Provider setup	thoth model or Providers guide
Platform setup	thoth gateway setup or Messaging docs
MCP servers	thoth mcp list or MCP guide
Profiles	thoth profile list or Profiles docs
Cron jobs	thoth cron list or Cron docs
Memory	thoth memory status or Memory docs
Env variables	thoth config env-path or Env vars reference
CLI commands	thoth --help or CLI reference
Gateway logs	~/.thoth/logs/gateway.log
Session files	thoth sessions browse (reads PostgreSQL sessions table; upstream reads state.db)
Source code	~/.thoth/thoth-agent/

---

Contributor Quick Reference

For occasional contributors and PR authors. Full developer docs: https://thoth.519lab.com/docs/developer-guide/

Project Layout

thoth-agent/
├── run_agent.py          # AIAgent — core conversation loop
├── model_tools.py        # Tool discovery and dispatch
├── toolsets.py           # Toolset definitions
├── cli.py                # Interactive CLI (ThothCLI)
├── thoth_state.py       # Session store (PostgreSQL in this fork; SQLite upstream)
├── agent/                # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch
├── thoth_cli/           # CLI subcommands, config, setup, commands
│   ├── commands.py       # Slash command registry (CommandDef)
│   ├── config.py         # DEFAULT_CONFIG, env var definitions
│   └── main.py           # CLI entry point and argparse
├── tools/                # One file per tool
│   └── registry.py       # Central tool registry
├── gateway/              # Messaging gateway
│   └── platforms/        # Platform adapters (telegram, discord, etc.)
├── cron/                 # Job scheduler
├── tests/                # ~3000 pytest tests
└── website/              # Docusaurus docs site

Config: ~/.thoth/config.yaml (settings), ~/.thoth/.env (API keys).

Adding a Tool (3 files)

1. Create tools/your_tool.py:

import json, os
from tools.registry import registry

def check_requirements() -> bool:
    return bool(os.getenv("EXAMPLE_API_KEY"))

def example_tool(param: str, task_id: str = None) -> str:
    return json.dumps({"success": True, "data": "..."})

registry.register(
    name="example_tool",
    toolset="example",
    schema={"name": "example_tool", "description": "...", "parameters": {...}},
    handler=lambda args, **kw: example_tool(
        param=args.get("param", ""), task_id=kw.get("task_id")),
    check_fn=check_requirements,
    requires_env=["EXAMPLE_API_KEY"],
)

2. Add to toolsets.py → _THOTH_CORE_TOOLS list.

Auto-discovery: any tools/*.py file with a top-level registry.register() call is imported automatically — no manual list needed.

All handlers must return JSON strings. Use get_thoth_home() for paths, never hardcode ~/.thoth.

Adding a Slash Command

1. Add CommandDef to COMMAND_REGISTRY in thoth_cli/commands.py
2. Add handler in cli.py → process_command()
3. (Optional) Add gateway handler in gateway/run.py

All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically.

Agent Loop (High Level)

run_conversation():
  1. Build system prompt
  2. Loop while iterations < max:
     a. Call LLM (OpenAI-format messages + tool schemas)
     b. If tool_calls → dispatch each via handle_function_call() → append results → continue
     c. If text response → return
  3. Context compression triggers automatically near token limit

Testing

python -m pytest tests/ -o 'addopts=' -q   # Full suite
python -m pytest tests/tools/ -q            # Specific area

• Tests auto-redirect THOTH_HOME to temp dirs — never touch real ~/.thoth/
• Run full suite before pushing any change
• Use -o 'addopts=' to clear any baked-in pytest flags

Windows contributors: scripts/run_tests.sh currently looks for POSIX venvs (.venv/bin/activate / venv/bin/activate) and will error out on Windows where the layout is venv/Scripts/activate + python.exe. The Thoth-installed venv at venv/Scripts/ also has no pip or pytest — it's stripped for end-user install size. Workaround: install pytest + pytest-xdist + pyyaml into a system Python 3.11 user site (/c/Program Files/Python311/python -m pip install --user pytest pytest-xdist pyyaml), then run tests directly:

export PYTHONPATH="$(pwd)"
"/c/Program Files/Python311/python" -m pytest tests/tools/test_foo.py -v --tb=short -n 0

Use -n 0 (not -n 4) because pyproject.toml's default addopts already includes -n, and the wrapper's CI-parity story doesn't apply off-POSIX.

Cross-platform test guards: tests that use POSIX-only syscalls need a skip marker. Common ones already in the codebase:

• Symlink creation → @pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows") (see tests/cron/test_cron_script.py)
• POSIX file modes (0o600, etc.) → @pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows") (see tests/thoth_cli/test_auth_toctou_file_modes.py)
• signal.SIGALRM → Unix-only (see tests/conftest.py::_enforce_test_timeout)
• Live Winsock / Windows-specific regression tests → @pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")

Monkeypatching sys.platform is not enough when the code under test also calls platform.system() / platform.release() / platform.mac_ver(). Those functions re-read the real OS independently, so a test that sets sys.platform = "linux" on a Windows runner will still see platform.system() == "Windows" and route through the Windows branch. Patch all three together:

monkeypatch.setattr(sys, "platform", "linux")
monkeypatch.setattr(platform, "system", lambda: "Linux")
monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic")

See tests/agent/test_prompt_builder.py::TestEnvironmentHints for a worked example.

Extending the system prompt's execution-environment block

Factual guidance about the host OS, user home, cwd, terminal backend, and shell (bash vs. PowerShell on Windows) is emitted from agent/prompt_builder.py::build_environment_hints(). This is also where the WSL hint and per-backend probe logic live. The convention:

• Local terminal backend → emit host info (OS, $HOME, cwd) + Windows-specific notes (hostname ≠ username, terminal uses bash not PowerShell).
• Remote terminal backend (anything in _REMOTE_TERMINAL_BACKENDS: docker, singularity, modal, daytona, ssh, vercel_sandbox, managed_modal) → suppress host info entirely and describe only the backend. A live uname/whoami/pwd probe runs inside the backend via tools.environments.get_environment(...).execute(...), cached per process in _BACKEND_PROBE_CACHE, with a static fallback if the probe times out.
• Key fact for prompt authoring: when TERMINAL_ENV != "local", every file tool (read_file, write_file, patch, search_files) runs inside the backend container, not on the host. The system prompt must never describe the host in that case — the agent can't touch it.

Full design notes, the exact emitted strings, and testing pitfalls: references/prompt-builder-environment-hints.md.

Refactor-safety pattern (POSIX-equivalence guard): when you extract inline logic into a helper that adds Windows/platform-specific behavior, keep a _legacy_<name> oracle function in the test file that's a verbatim copy of the old code, then parametrize-diff against it. Example: tests/tools/test_code_execution_windows_env.py::TestPosixEquivalence. This locks in the invariant that POSIX behavior is bit-for-bit identical and makes any future drift fail loudly with a clear diff.

Commit Conventions

type: concise subject line

Optional body.

Types: fix:, feat:, refactor:, docs:, chore:

Key Rules

• Never break prompt caching — don't change context, tools, or system prompt mid-conversation
• Message role alternation — never two assistant or two user messages in a row
• Use get_thoth_home() from thoth_constants for all paths (profile-safe)
• Config values go in config.yaml, secrets go in .env
• New tools need a check_fn so they only appear when requirements are met