Havuz

TRACES.md — AGENTS.md, but for what agents did. A simple, open format for recording what AI agents did, for error analysis and self-optimiza

A lightweight coding agent for teaching, research, and experimentation

A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Portal - public MCP endpoint

DrugTargetWorld: a synthetic biobank for training and benchmarking AI scientists on end-to-end drug target discovery. Paper: arXiv:2610.0955

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Open-source, local-first AI team workspace. Several AI models work together in one conversation, each with its own provider, model and tool

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

Same-brief agentic build comparison: GPT-6 Astra High vs Gemini 3.8 Flash High building a playable 3D AI civilization simulation game.

Redpen makes coding agents prove they are actually done.

Exploring agent "thinking" animation.

Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillat

Self-hosted sandboxes for AI agents: Docker, Firecracker or Apple Virtualization microVMs. Your real API keys never enter the sandbox. Part

Start with a concept, not a stack. A harness-agnostic protocol that scaffolds greenfield projects from a rigorous concept instead of a chain

Self-hosted AI company OS for solo founders: autonomous agents, ERPNext business memory, and owner-visible governance.

Open-source Windows AI IDE built with .NET 10 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-healin

Tell an AI to edit your video and watch it happen. A real non-linear editor with a timeline, plus 83 tools an agent can call over MCP — work

Agentizable: an open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.

Self-hosted workspace that runs several AI coding CLIs (OpenCode, Codex, Claude Code, Gemini) side by side in persistent rooms.

DSoR (Data System of Record): the governed layer between AI agents and a company's real systems. It checks permissions, limits and approvals

A minimal, explicit, provider-safe harness for the Pi coding agent

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and

Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.

An autonomous multi-agent AI workspace that automates job hunting. Features native PDF parsing, ATS scoring, multi-engine job scraping, Play

Your Local Email Agent

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Terminal-first workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status per project, code viewer + Git, sy

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic

A more autonomous, more persistent, and easier alternative to OpenClaw/Hermes. Give it a task and it will carry it out, even if it takes

Generate schema-valid Paperclip agent-company bundles from a Markdown brief.

a truly open experimental coding harness

Open source release of Data Science Agents that can analyze and transform datasets as well as train and infer models to augment your data sc

A production-grade reference implementation for LLM agent systems: flow declared as a LangGraph graph, Pydantic AI for typed agents, generat

Native terminal workspace for parallel AI coding agents. Git worktree isolation, persistent sessions, embedded browser tabs, and mobile remo

Caesar — autonomous AI research agent with graph-based deep web exploration and adversarial answer synthesis. Open-source alternative to Cha

AI-assisted rescue boot USB — a Ventoy multi-boot drive on Ubuntu 24.04 with offline LLM inference (Ollama + llama.cpp), pre-installed agent

Private, local-first Android AI workspace: chat, voice and autonomous agents with your own API keys. No telemetry, no analytics, no bundled

Free, open-source macOS menu-bar app that uses lifecycle hooks to keep your Mac awake while Claude Code, Codex, OpenCode, or GitHub Copilot

Multi-agent skill for Claude Code that delegates tasks to Google Antigravity CLI — web search, image gen, codebase analysis, 40+ science dat

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

Give agents access to virtual hardware.

Enterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-t

The Virtual Filesystem Interface for AI Agents

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, expla

Run a team of AI agents on your own computer. Your files, browser sessions and passwords stay local. Works with Claude Code, Codex, hosted o

Build and operate production-safe agents that run in your own environment.

Open-source agentic AI operating layer for hospital operations — multi-agent orchestration over FHIR-connected HIS data, built on LangGraph