#agent-harness Repositories
Discover 53 active open source GitHub repositories tagged with #agent-harness, accumulating 439,597 total stars (averaging 8,294 stars per project). Leading this topic is infiniflow/ragflow with 94,501 stars.
55 repositories total
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
๐คฏ LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses. They take on work by themselves and get better every week.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
RocketRide is an open-source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test, and publish durable agents that scale in production.
Open-source agentic workspace enterprises can make their own. Connect the systems you already run โ 100+ integrations, MCP, chat tools, apps, browser, local files โ with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
Coolest app to use agents, local, multi-provider, and open-source alternative to Grok bot. Build custom worlds for your Claude Code and Codex-like agents.
Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw, and Hermes, with projects, scheduled automations, and connectors. Free app for macOS and Windows; use built-in models or your own API keys.
Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
โจ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
The control plane for 24/7 always-on agents. Turn long-horizon goals into verifiable results across Codex, Claude Code, and custom runtimesโfrom local SQLite to team scale.
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
Same agent, smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).
Roubao 2.0 for iPhone: an open-source iOS AI agent with owner-authorized Micro-X UI control, custom models, resumable tasks, and PDF reports. No Wi-Fi, jailbreak, computer, or extra hardware required at runtime (Mac + USB required for setup). Legacy Android version retained.
Multi-agent graph harness for Claude Code, Codex, and other coding agents. Separate agents review and test the work. Runs locally on your subscription.
Waku Agent is an open-source AI agent harness you own: loop, memory, evals, and an always-on layer (event inbox, timers, approvals, outbox), in code that stays readable.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
A living pixel-art station where real AI agents do real work. Local-first desktop agent harness โ bring your own key, watch your crew actually run.
For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.
AI coding harness for desktop, terminal and CI. Maps your repo, edits code by symbol through AST and LSP, then runs your checks. Any model or the plan you already pay for. Get it at https://empryo.com
๐ Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent workflows.
Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.
Tianshu Harness is a terminal programming agent. The core question it is designed to answer is: How can a model deliver reliablyโwith no goal drift, completion backed by evidence, and verification forming a closed loop, rather than saying โIt should be fixed nowโ? To achieve this, it establishes a cognitive execution environment (CVM) between the model and the real world, externalizing goals, state, evidence, resources, permissions, and termination conditions from the conversation history for continuous runtime management. It is also highly optimized for DeepSeek V4.
Open-source AI agent harness in native Rust โ GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
๐ค MateClaw โ Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.
The operational superset of Pi Coding Agent โ everything in Pi, plus observability, governance, recovery, evaluation, and multi-agent orchestration.
Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.
Open-source, multi-platform harness for AI agents โ a native, multi-threaded operatorโs console (JVM, not Electron) to run Claude Code, Codex, Gemini, or OpenCode with a real browser, terminal, editor, secrets, and 200+ MCP tools. Built for enterprises, science, and research.
Enterprise Agent Harness & MCP Gateway: connect APIs, databases, file servers and 600+ connectors (SAP, Odoo, Etsyโฆ) to Claude, ChatGPT, Microsoft Copilot and your agents. Memory, skills, knowledge graph, SSO/RBAC, audit log and governance built in. Your AI company brain.
๐ ๏ธ The meta-harness for AI agents โ scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
A multiplayer harness that adapts to the way you work. Agents, apps, and workflows your team sharesโaccessible from Slack, Telegram, WhatsApp, Teams, email, the web, or your own AI agent.
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
mu (ฮผ): most of what a coding agent decides isnโt code. mu hands 40 kinds of yes/no decisions to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.
Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references โ English and Chinese.
Official Code for OpenVLHarness: Real-World Visual Agentic Tool-Use with Multimodal Memory
Frequently Asked Questions
What is the most popular #agent-harness repository on GitHub?
The top ranked open source #agent-harness project on GitHub is infiniflow/ragflow with 94,501 stars. RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Which programming languages are most used in #agent-harness repositories?
Among the top ranked #agent-harness projects on GitHub, the most common programming languages are TypeScript, Python, Go, JavaScript.
How is the #agent-harness repository ranking calculated?
We track 53 active open source repositories tagged with #agent-harness (500+ stars), totaling 439,597 stars with an average of 8,294 stars per repository. Rankings update daily from the GitHub API.