traylinx

Unified LLM proxy for AI agents. Route all model requests through http://localhost:18080/v1. Provides FREE access to Gemini CLI, Claude CLI, Codex, and Vibe via your existing subscriptions. Includes Intelligent Auto-Routing (Cortex) for autonomous model selection, a self-optimizing Lab, token conservation, and a management dashboard. Use when: (1) making LLM calls, (2) switching between CLI/Local/Cloud providers, (3) attaching local files to prompts, (4) needing intelligent routing, or (5) auto-setting up the best available models.

Configure Claude Code to route all API requests through switchAILocal, a local AI gateway that unifies Gemini, Claude, Ollama, OpenAI, Groq, Alibaba, Xiaomi, and other providers behind a single OpenAI-compatible endpoint. Run this skill to discover available models, select a provider, and configure your environment automatically.

Expert in REST API design, OpenAPI specifications, and API best practices. Has tools to validate specs and generate OpenAPI from Go structs.

Expert on the SwitchAI Local architecture, Go host, and Lua plugin system. Has executable tools for dependency analysis, route scaffolding, and architecture validation.

Expert in Testing Methodologies (Go testing, Vitest, Playwright, TDD). Has tools for coverage analysis and test generation.

Specialized instructions for writing and optimizing Jevvel Labs blog posts. Focuses on SEO, engaging introductions, and the unique 'cyber-brutalist' aesthetic.

Expert in systematic debugging, root cause analysis, profiling, and performance troubleshooting. Use when stuck on bugs, investigating errors, or optimizing performance.

Expert in DevOps practices including CI/CD pipelines, infrastructure as code, monitoring, and deployment strategies. Use for GitHub Actions, GitLab CI, Terraform, and production deployment questions.

Use when configuring, installing, verifying, or troubleshooting optional Headroom MCP compression with Lope or Lope-installed agent hosts. Covers opt-in Headroom MCP registration, large validator/tool-output compression, Claude/Codex/Cursor MCP status checks, and the `headroom-ai[mcp]` dependency when the user asks for it.

Multi-CLI validator ensemble for AI work. Use for multi-phase sprints, single-shot cross-model checks, autonomous flow graphs, evidence gates, team management, persistent finding memory, council deliberation, and self-update. Any AI CLI implements, any AI CLI validates. 15 built-in CLI adapters plus infinite custom providers via JSON config.

Use Lope when cross-model perspective helps: multi-phase sprints, flow graphs, ask/review/vote/compare/pipe, team, lope memory, lope deliberate, gate/check, update, or Headroom setup. Trigger on 3+ phases, consequential multi-file work, second opinions, artifact review, consensus/SARIF, ADR/PRD/RFC/build-vs-buy/migration, A/B or yes/no choices, pipes, roster changes, updates, or Headroom. Skip trivial single edits, pure conversation, urgent firefighting.

Run a declarative GRAPH workflow where AI agents negotiate autonomously — no human gates. A flow is a DOT graph: nodes are agent turns, ensemble reviews, shell verify-steps, or judge/routers; edges carry conditions and loops. Each node dispatches into lope's existing multi-CLI executors (any CLI implements, the ensemble votes). Bounded by per-node and graph-wide visit caps so an unsupervised run can never loop forever. Use when the user wants to shape HOW agents collaborate (fan-out proposers, consensus, fix-loops) as editable, reviewable, version-controlled process — not a fixed linear sprint.

Manage the validator team (add, list, remove, smoke-test) via CLI flags. Trigger on any user request about adding, removing, configuring, enabling, disabling, or testing a validator/teammate/CLI on lope — including 'add openclaw to lope', 'remove ollama from the team', 'list validators', 'is my new provider working', 'hook up my mistral pod', 'what CLIs are configured', OR the user pasting a curl command and saying 'add this'. Works for subprocess binaries (any local CLI), OpenAI-compatible HTTP endpoints (pods, gateways, cloud APIs), and pasted curl commands via `--from-curl`. The LLM translates natural language into the right invocation — the end user never edits JSON.

Draft a sprint doc via multi-round negotiation with AI validators. Lope sends your plan to other AI CLIs (Claude, Gemini, OpenCode, Codex, Mistral Vibe, Aider, Ollama, Goose, llama.cpp, Open Interpreter, Copilot, Amazon Q, or any HTTP API) for independent review. Majority vote. No single-model blindspot. Works for engineering, business (marketing, finance, ops), and research domains.

Print the complete lope reference into the current session — all modes, flags, domains, env vars, slash-command vs natural-language invocation per host, troubleshooting, and hard rules for agents. Use when the user asks 'how does lope work', 'what can lope do', 'what are lope's flags', or anything that needs authoritative lope documentation. Prefer this over guessing from memory.

Run a sprint with zero-human swarm orchestration. First select implementation agents and escalation agents, then Lope executes phases without further human input. Use when the user says implement the whole sprint, stay out of the loop, use Claude/OpenCode or specific CLIs for escalations, or wants autonomous sprint backlog completion.

Use `tytus` by Traylinx — a CLI, tray, and TytusOS desktop for private AI pods, OpenAI-compatible gateway access, pod lifecycle, Files, channels, terminal, and MCP integration.