Designing, evaluating, and shipping autonomous AI agents.
7657 posts
An open, thin, model-agnostic harness for long-horizon autonomous AI research. Built on Goose.
Local coding-agent orchestrator — DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/l...
Local-first MCP memory server. Indexes Claude Code/Cowork/Telegram chats; any MCP-compatible AI agent (Cursor, Cline, Continue) can search t...
Database MCP server for MySQL, MariaDB, PostgreSQL, and SQLite - with builtin PII redaction and write-prevention
Inspectable local project memory for AI coding agents.
Context Runtime — a database query planner for LLM context. Decides what a model sees before it answers; plans it, runs it through reused su...
A single CLI to keep your local repositories, AI agent skills, and MCP server configurations in sync.
Universal memory runtime for AI agents
Open library of legal AI skills (SKILL.md) for MCP-compatible agents — 39 jurisdictions, 200+ plugins, Apache-2.0.
Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.
Open-source MCP knowledge mesh - self-host your second brain, expose it to AI agents, federate with peers.
Local AI operations console for supervised agent work.
