Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj
Minimal project memory and validation harness for AI coding agents.
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj
A ContextOps toolkit for AI coding agents.
Generate a standard .agents folder and AGENTS.md pointer in any agent-assisted project.
Bootstrap a Leji context layer for AI-native teams: npm create leji runs leji init .
Reference SDK and CLI for Leji, the open specification for the shared context layer of AI-native teams: validate, index, changelog, freshness, conformance, viewer, init, adopt, detect, start, ci, and agent.
Deterministic-first, plain-markdown knowledge vault. Code does the bulk transform. The LLM only touches the irreducibly-semantic 20%. Native grep plus BM25 retrieval, zero MCP on the vault.
Network-wide task tracking system for Wood Fired Games
Technical Knockout CLI, MCP server, and Codex installer for capability replication.
Model Context Protocol server for Agentic Task System — exposes the task app you already use to any MCP client, backed by hybrid + RRF retrieval. Storage-agnostic over the ATS adapter contract.
Persistent typed memory for AI coding agents — install & forget: auto-inject context via git hooks, 13 memory types, confidence tracking, conflict detection, grounded QA, codebase graphs
Local stdio MCP server for Leji: retrieve the spec and schemas, and run validation and conformance against a context layer, natively from an AI agent.
Memory and Context Orchestration for Coding Agents
Adds /brief for generating and updating AI coding agent project context. Works with Pi, Claude Code, and Codex.