agent-harness

infiniflow/ragflow

RAGFlow pairs deep document understanding with agentic RAG — RAGFlow combines retrieval-augmented generation with agent capabilities, grounding answers in traceable citations from complex documents. It targets teams building LLM apps that need reliable, well-cited knowledge bases rather than simple chatbots, with multi-language docs and a cloud-hosted option.

lobehub/lobehub

LobeHub turns team chats into a home for self-improving agents — LobeHub adds 'super-agents' directly into chat tools teams already use, letting them take on tasks autonomously and improve over time through loop engineering and skills. It targets teams wanting proactive AI collaborators for task management rather than another standalone chatbot, with MCP and multi-agent support built in.

Mintplex-Labs/anything-llm

A local-first LLM workspace that turns documents into working agents — AnythingLLM bundles RAG chat, multi-user support, and configurable AI agents into one self-hosted app, aimed at people who want to run document-grounded chat and agentic workflows locally instead of relying on hosted AI services. It targets self-hosters and teams needing private, multimodal, agent-capable LLM tooling without complex setup.

agentscope-ai/QwenPaw

QwenPaw: a self-hosted personal AI assistant with layered memory — QwenPaw is a self-hostable personal AI assistant built on Alibaba's agentscope stack, deployable locally or in the cloud with no mandatory API key via its built-in QwenPaw-Flash models or Ollama/LM Studio. It adds a three-layer memory system (working context, full history, self-evolving knowledge base), sandboxed security guards, and multi-agent orchestration, aimed at users wanting a private, extensible assistant across chat channels.

HarnessMD/munder-difflin

An open-source office of coding-agent clones on your laptop — Munder Difflin is a free, local-first multi-agent harness that wraps Claude Code, Codex, Gemini CLI, Grok, OpenCode, Cursor and more, using your existing subscriptions. It visualizes agents as avatars on a shared office floor, coordinated by a 'clone' that routes messages and remembers context while you're away.

Orkas-AI/Orkas

A Desktop AI Team That Coordinates Claude Code, Codex and More — Orkas is an open-source, local-first desktop app where a Commander agent splits goals into to-dos and routes them to 16 built-in specialists plus external agents like Claude Code, Codex, OpenCode, OpenClaw and Hermes. Projects keep memory and files persistent, auto-advance and scheduled automations keep work moving, and all data stays on your machine.

mvschwarz/openrig

Turning scattered AI coding agents into a managed team — OpenRig lets you define a persistent team of Claude Code and Codex agents in YAML, run them under one lead agent, and keep shared context and work organized instead of juggling separate terminal sessions. Aimed at developers running multi-agent coding setups who want coordination, not chaos.

HarnessRouter/harnessrouter

One API to run Codex, Claude Code, Hermes and more agent harnesses — HarnessRouter CE is a self-hosted, Apache-2.0 gateway that unifies agent harnesses like Codex, Claude Code, Hermes, PI and DSH behind a single API with sessions, streaming, files, cancellation and failure handling. It implements the open Unified Harness Protocol (UHP) and is OpenAI Responses-compatible, aimed at teams building agent products who want to avoid harness-specific integration work.

androoAGI/starnet

Build AI agent crews inside a pixel-art space station UI — StarNet is a local-first desktop app where a pixel-art station's rooms, hallways and objects literally represent capability-scoped agent teams, handoff permissions, and real grants. You bring your own API keys and watch multiple bounded agents run concurrently with real model calls and tools, not simulated activity.

HelpCode-ai/anythingmcp

Self-hosted gateway that wraps 517 APIs as MCP tools — AnythingMCP connects REST/OpenAPI, SOAP, GraphQL, OData and SQL systems to Claude, ChatGPT and Copilot without writing a custom MCP server. It ships 517 ready-made connectors, including SAP, Etsy and Amazon Seller, with 23 needing no API key, plus RBAC, SSO and audit logs for enterprise use.

Agent-Field/CodeAF

A coding harness built to squeeze frontier results from open models — CodeAF is a single-binary coding harness tuned for open models like DeepSeek, Qwen, GLM, Kimi and MiniMax rather than closed APIs. It replaces juggling multiple terminal agents with one window that tracks work across projects, letting you hand off tasks and step in only when needed. Early preview, Apache 2.0, runs on macOS/Linux/Windows.

uclanlp/OpenVLHarness

Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

rudderlabs/devbox

Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.

Balanov/uncut

The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.