Havuz

Open Source Data Science Agent for Discord and Slack

Agent dashboard runs reliability scans, skills, and network access probes.

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

Outworked - Cozy Office for Claude Code

Monet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a n

A senior microsoldering technician, available to every repair shop from the seasoned pro to the apprentice. Powered by Claude Opus 5

A self-hosted workspace where people and AI agents work together

Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

Local, provider-agnostic agentic hub: an orchestrator and a squad of little monsters on your machine

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama

Agentic event-venue operator demo built on MongoDB Atlas. Showcases three-layer memory (long-term, short-term, shared), hybrid retrieval wit

Self-hosted web viewer for Claude Code session transcripts — read, search, replay, and audit every session you have ever run

Run-aware token governance for multi-agent systems.

Voice-first Mac assistant that uses the computer for you. GPT-Live-1 voice behind a wake word; brains: Codex, Claude Code, an API or a local

Agent Reliability Analyzer: deterministic scanner that finds and fixes AI agent reliability failures

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s

Deterministic agent reliability detection rules for the Trustabl Analyzer

Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process

Your AI agents, always on, working together. Claude Code, Antigravity and Codex on your own computer.

Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model acc

One command to cut token usage by up to 50%+

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.

Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

The open source data science agent for Discord and Slack

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Understanding CLAUDE.md, MEMORY.md, SKILLS.md, SOUL.md, and Related Prompting Mechanisms

Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking

The agent harness for Ruby applications. Durable sessions, streaming, human-in-the-loop approval, compaction, structured output, sub-agents,

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

Autonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

Evolving agent harnesses: a research program on how far N orchestrated calls of a small model can rival a frontier model. We evolve the harn

Claude Code Skills, Agents & Plugins — UitKit

Behavior guidelines that stop your AI coding agent from overengineering, hallucinating, and breaking things

Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.