Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.
Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.
Exibindo SKILL.md
SKILL.md
Instruções da origem · Visualização somente leitura
name
agent-recall
description
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
["save","save session","/arsave","/arstart","remember this","recall","what did we do last time","load context","start session","end session","checkpoint","保存","记住","上次做了什么","加载上下文"]
skip
["don't save","skip memory","no need","不用记","算了"]
AgentRecall v3.4.30 — Usage Guide
AgentRecall is a persistent memory system. Default surface: 5 tools (two verbs + three essentials). Full surface: 18 tools via npx agent-recall-mcp --full. This guide describes how and when to use them.
Two-verb model:session_start (inhale — load context) and session_end (exhale — save and compound). Everything else is available but secondary; most agents never need more than the default 5. See Automaticity Law below.
Setup
AgentRecall requires the MCP server to be running. If tool calls fail with "unknown tool", the human needs to install it first.
Visual setup guide (all 13 clients, copy-paste prompts): open warroom/install.html from the repo, or the GitHub raw link in a browser.
Installation (human runs once)
Claude Code:
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
active_rooms — top 5 palace rooms by salience (with staleness flag + last_updated)
(Palace = your project's long-term knowledge store, organized into topic rooms like "architecture", "goals", "blockers". Salience = relevance score 0-1 based on recency, access frequency, and connections. Rooms with stale=true haven't been updated in 7+ days.)
cross_project — insights from other projects matching current context
recent — today/yesterday journal briefs
watch_for — predictive warnings from past correction patterns + decision calibration
Read insights — these are battle-tested lessons. Follow them.
Read watch_for — these are patterns where you've been wrong before on this project. Adjust your approach.
Read recent to understand where the last session left off
Present a brief to the human: project name, last session summary, relevant insights
Example call:
session_start({ project: "auto" })
remember
When: You learn something worth keeping. A decision, a bug fix, an insight, a session note.
What it does: Auto-classifies your content and routes it to the right store:
Bug fix / lesson → knowledge store
Architecture / decision → palace room
Cross-project pattern → awareness system
Session activity → journal
You do NOT need to decide where it goes. Just describe what to remember.
How to use:
remember({
content: "We decided to use GraphQL instead of REST because the frontend needs flexible queries",
context: "architecture decision" // optional hint, improves routing
})
When: You need to find something from past sessions. A decision, a pattern, a lesson.
What it does: Searches ALL stores at once using Reciprocal Rank Fusion (RRF) — each source (palace, journal, insights) ranks internally, then positions merge so no single source dominates. Journal entries decay fast via Ebbinghaus curve (S=2 days); palace entries are near-permanent (S=9999). Returns ranked results with stable IDs.
Feedback: After using results, rate them. Ratings use a Bayesian Beta model — the mathematically optimal estimate of true usefulness:
recall({
query: "auth patterns",
feedback: [
{ id: "abc123", useful: true }, // Beta(2,1) → ×1.33 next time
{ id: "def456", useful: false } // Beta(1,2) → ×0.67 next time
]
})
Feedback is query-aware — rating something "useless" for one query doesn't penalize it for unrelated queries.
session_end
When: End of session, after work is done.
What it does in one call:
Writes daily journal entry
Updates awareness with new insights (merge or add)
Consolidates decisions/goals into palace rooms
Archives demoted insights (preserved, not deleted)
How to use:
session_end({
summary: "Built auth module with JWT refresh rotation. Fixed CORS bug.",
insights: [
{
title: "JWT refresh tokens need httpOnly cookies — localStorage is vulnerable",
evidence: "XSS attack vector discovered during security review",
applies_when: ["auth", "jwt", "security", "cookies"],
severity: "critical"
}
],
trajectory: "Next: add rate limiting to API endpoints"
})
Rules for insights:
1-3 per session. Quality over quantity.
Must be reusable. "Fixed a bug" is NOT an insight. "API returns null when session expires — always null-check auth responses" IS an insight.
applies_when keywords determine when this insight surfaces in future sessions across ALL projects.
Return fields:
journal_written — boolean, true if journal entry was saved
awareness_updated — boolean, true if any insight was stored
palace_consolidated — boolean, true if palace rooms were updated
insights_processed — number of insights accepted
quality_warnings — advisory warnings if insights are too short, lack evidence, or use event-verb phrasing (never blocks saves)
card — formatted save summary (box-drawing card)
merge_suggestions — array of similar recent entries (optional)
check
When: Before executing a complex task where you might misunderstand the human's intent. Also for tracking decision quality over time.
What it does:
Records your understanding of the goal
Returns watch_for — patterns from past corrections on this project
Returns similar_past_deltas — times you misunderstood similar goals before
After human responds, record the correction for future agents
Optionally tracks decision trails with prior/posterior/evidence for calibrated judgment
Two-call pattern (correction tracking):
Call 1 — before work:
check({
goal: "Build REST API for user management",
confidence: "medium",
assumptions: ["User wants REST, not GraphQL", "CRUD endpoints", "PostgreSQL backend"]
})
Read the watch_for response. If it says "You've been corrected on API style 3 times", ASK the human before proceeding.
Call 2 — after human corrects (if they do):
check({
goal: "Build REST API for user management",
confidence: "high",
human_correction: "Actually wants GraphQL, not REST",
delta: "API style preference — assumed REST, human prefers GraphQL"
})
This feeds the predictive system. Future agents on this project will get warnings.
Decision trail (Bayesian-inspired calibration):
For major decisions, track confidence and outcome to calibrate judgment over time:
check({
goal: "Use GraphQL instead of REST",
confidence: "medium",
prior: 0.7, // initial confidence (0-1)
evidence: [
{ factor: "Frontend needs flexible queries", direction: "supports", weight: 0.2 },
{ factor: "No GraphQL experience on team", direction: "weakens", weight: 0.3 }
],
posterior: 0.55, // updated confidence after evidence
outcome: "rejected" // final result: "confirmed", "rejected", "partial", or free text
})
When outcome is provided, the decision trail is persisted to the palace decisions room. After 3+ closed decisions, session_start surfaces calibration warnings: "Your priors average 0.8 but outcomes average 0.5 — you're overconfident."
These tools are available when the server is started with --full. Most agents never need them — the default 5 tools carry all compounding memory value. Enable --full for project narrative tracking (pipeline), procedural rules (skills), status dashboards, context caching, or first-time bootstrap.
project_board
When: Start of a new session when you don't know which project to work on.
What it does: Scans all projects and returns a status board — last activity date, pending work, active blockers. Use this before session_start to pick which project to load.
project_board()
project_status
When: Quick check on a specific project's health without loading full context.
What it returns: Last trajectory, active blockers, palace room freshness (stale flag), next steps, summary line. Lighter than session_start — no awareness or cross-project loading.
project_status({ project: "auto" })
bootstrap_scan
When: First time using AgentRecall, or when /arstatus shows an empty board.
What it does: Scans your machine for existing projects — git repos, Claude AutoMemory (~/.claude/projects/), and CLAUDE.md files. Returns a structured report of what CAN be imported. Read-only, no writes.
What it scans:
~/Projects/, ~/work/, ~/code/, ~/dev/, ~/src/, ~/repos/, ~/github/ for git repos
~/.claude/projects/ for Claude AutoMemory (user profile, project memories, feedback)
CLAUDE.md files in project roots
How to use:
bootstrap_scan()
Returns:projects (array of discovered projects with importable items), global_items (user profile), stats (totals + scan duration)
bootstrap_import
When: After reviewing bootstrap_scan results, to import selected projects.
What it does: Creates AgentRecall entries for discovered projects — palace rooms, identity.md, knowledge entries from Claude memory, initial journal from git history.
How to use:
bootstrap_import({
scan_result: "<JSON from bootstrap_scan>",
project_slugs: ["my-app", "api-server"], // optional: import only these
item_types: ["identity", "architecture"] // optional: import only these types
})
CLI equivalent:
ar bootstrap # scan and show what's available
ar bootstrap --dry-run # preview what would be imported
ar bootstrap --import # import all new projects
ar bootstrap --import --project my-app # import one project
What gets imported per project:
identity — palace identity.md from project name + description + language
memory — Claude AutoMemory .md files → palace knowledge room
Scan is read-only — never writes to your machine or to AgentRecall
Import only writes to ~/.agent-recall/, never modifies source files
Skips .env, credentials, .pem, .key files — never reads secrets
Projects already in AgentRecall are skipped (no double-import)
Session Flow
Start of session
1. session_start() → load context, read insights and warnings
2. Present brief to human → "Last session: X. Insights: Y. Ready."
3. check() if task is complex → verify understanding before work
During work
4. remember() when you learn something → auto-routes to right store
(stores: journal for daily activity, palace rooms for persistent decisions, awareness for cross-project insights)
5. recall() when you need past context → searches everything
6. check() before major decisions → verify understanding
End of session
7. check() with corrections if any → record what human corrected
8. session_end() → save journal + insights + consolidation
9. Done — all data saved locally (only push to git if user explicitly asks)
How Memory Compounds
Each layer feeds the next. The system gets better the more you use it.
SAVE: remember("JWT needs httpOnly cookies")
→ Auto-named: "lesson-jwt-httponly-cookies-security"
→ Indexed in palace + insights
→ Auto-linked to "architecture" room (keyword overlap)
→ Salience scored: recency(0.30) + access(0.25) + connections(0.20) + ...
RECALL: recall("cookie security") — 3 sessions later, different project
→ Finds the JWT insight via keyword match + graph edge traversal
→ Agent rates it useful → feedback boosts future ranking
→ Next recall on similar query → this result surfaces higher
COMPOUND: After 10 sessions
→ 200-line awareness contains cross-validated insights
→ watch_for warns about past mistakes before they repeat
→ Corrections auto-promote to awareness at 3+ occurrences
→ Graph connects related memories across rooms automatically
Best Practices
Call session_start at the beginning. Insights from past sessions prevent repeated mistakes.
Call session_end when done. If the session produced decisions, insights, or corrections, save them.
Insights should be reusable. Write them for a future agent who has never seen this project.
Match the human's language. If they write in Chinese, save in Chinese.
Don't over-save. 1-3 insights per session. 1-2 remember calls during work. More is noise.
Rate your recall results. Feedback makes future retrievals better.
Use check for ambiguous tasks. 5 seconds of verification beats 30 minutes of wrong work.
Read watch_for warnings. If session_start or check returns warnings, adjust your approach.
Run bootstrap on first install. If /arstatus shows no projects, bootstrap_scan discovers what's already on your machine and imports it in seconds.
Check active_rooms in session_start. Palace rooms with high salience contain your project's most important decisions and patterns. Rooms marked stale may need updating.
Storage
All data is local markdown + JSON at ~/.agent-recall/. No cloud, no telemetry, no API keys.
All platforms use the same tools. No platform-specific behavior.
Why 5 Default Tools
The Automaticity Law (measured on the live corpus — 44 projects, 221 journals, 81 corrections, 2026-06-12): push channels (session_start, session_end, correction hooks, ambient recall) showed repeated behavior-changing usage across weeks of real agent sessions. Pull channels — check_action, skill_recall, pipeline_*, memory_query — had zero organic calls, including from the agent that built them.
Every extra tool in the default surface burns tool-definition tokens every session for zero behavioral return. The two-verb model (inhale = session_start, exhale = session_end) carries all compounding memory value. Everything else is available via --full for agents and workflows that explicitly need it.
Corollary: wire before write — a primitive without an automatic trigger will not be used.
Security & Privacy
Zero network: No outbound HTTP requests, no telemetry, no analytics, no cloud sync. All operations are local filesystem reads/writes.
Zero credentials: No API keys, tokens, or environment variables required.
Scoped filesystem access: Reads/writes only to ~/.agent-recall/ (configurable via --root flag). Does not access files outside this directory unless the agent explicitly passes project-specific paths.
No code execution: The MCP server does not execute arbitrary code, run shell commands, or spawn child processes.
Transparent storage: All data is human-readable markdown and JSON. Inspect it anytime: ls ~/.agent-recall/ or open it as an Obsidian vault.
