File-based message queue for local agent-to-agent communication (Maildir-style)

Persistent Intelligence Infrastructure for AI Agents

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

Metis is a coding agent that boosts AI/LLM coding performance by 50%

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

Git-native memory for coding agents. Repo memory before the diff.

A CLI tool for automating BMAD-METHOD development workflows with Claude Code.

Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients

Interact seamlessly with GitLab repositories to manage merge requests and issues. Fetch details, add comments, and streamline your code review process with ease.

Swarm orchestration for claude code agents with a local brain that steers based on your preferences

Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

Workflow orchestration for AI coding agent swarms, from task to merged PR.

Lightweight coding agent written in Rust, optimized for memory footprint and performance

IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 20 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.