Automation

Enables coding agents to coordinate edits, reviews, and escalations without file locking conflicts

Expose declarative YAML-defined workflows as MCP tools over stdio

Turn any OpenAPI spec into an executable agent interface using graphs and semantic search.

Shared memory & coordination for AI coding agents — a blackboard, not an orchestrator.

Event-sourced ticket tracker + Jira reconciler, exposed as a Python library, CLI, and MCP server.

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Local MCP for Power Automate with browser-backed auth, target locking, review diff, and rollback.

Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

Serveur MCP pour l'orchestration de tâches distantes (SSH/SFTP) avec une file d'attente persistante.

Autonomous LLM build orchestrator that plans, edits, and verifies code across languages.

The drift harness as an MCP server. Offline, no key — a fixed reference an agent checks against.

Crash-proof LLM pipelines. Resumes from failure without a database.

Expose deterministic ChainWeaver flows as MCP tools without LLM calls between steps.

AI workflow error analysis for n8n, Make, Zapier, and 10+ platforms.

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

MCP server giving AI agents persistent SQLite memory that proves which lessons hold.

Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.

Schedule Docker builds via Windows Task Scheduler — survives VS Code terminal timeouts

Run scheduled LLM-written email digests from local files and feeds. Local-first MCP server.