Harness: open-source projects on GitHub
86 repositories on Harness, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Open-source SuperAgent
Open-source SuperAgent that explores, writes code, and creates solutions using sandboxes, memory, tools, and sub-agents.
★ 67,170 · PythonSTAGEHAND SDK FOR BROWSER WEB AGENTS
Stagehand provides TypeScript SDK for creating browser agents that can interact, search, extract, and fetch data from any website reliably across the web. It simplifies a
★ 26,054 · TypeScriptDeepSeek Harness Desktop
A desktop application for working with the DeepSeek Harness model, providing a convenient interface and local execution of AI tasks without web access.
★ 19,075 · TypeScriptMulti-user agent for work
TypeScript library for creating multi-user agents, simplifying collaborative work and interaction in AI projects.
★ 15,705 · TypeScriptMUNDER-DIFFLIN OFFICE OF AGENT
Munder-Difflin starts a local office of agents working with Claude Code and Codex.
★ 9,528 · TypeScriptTrueForge: Agent Engine
Open-source agent belt — a runtime that turns a large language model into a working agent.
★ 6,484 · TypeScriptEngineering Guide
Official guide to engineering practices in Harness: step by step from beginner to expert.
★ 6,173 · TypeScriptEve: Framework for Agents
Eve provides a TypeScript library for creating, testing, and deploying autonomous AI agents with tool and memory support.
★ 5,912 · TypeScriptFrontierAgent framework
FrontierAgent is an open framework for building agents with a native CLI‑TUI, ReAct support, and agent team work modes. It launches with a single command on macOS and Lin
★ 5,439 · PythonOPENAGENT: AI ASSISTANT OF THE FUTURE
openagent – the next level of personal AI assistant: LLM, RAG, and agent loops for computer, browser, and code work.
★ 5,150 · GoMODLENS — VISION FOR AI AGENTS
Converts images into structured JSON with OCR, markup, and semantic data so text LLMs can 'see'.
★ 4,980 · TypeScriptPLATFORM FOR AI AGENT LIFECYCLE
Solace Agent Mesh — platform for full AI agent lifecycle: build, test, deploy, monitor, improve. Hosts agents, runs their tools, and coordinates via event mesh with sessi
★ 4,923 · ShellAGENTA: AI AGENTS IN CHAT
Agenta is an open platform for creating AI agents via chat, sharing them, and running them on schedule or in response to app events.
★ 4,911 · TypeScriptDISCOVER HARNESSES: TOOLS
A collection of the best tutorials and utilities for working with wire harnesses and power systems.
★ 4,722Memory for AI Agents
The project provides long‑term memory for AI agents, allowing them to retain context between sessions and improve code generation quality based on real benchmarks.
★ 4,605 · TypeScriptNexent: AI Agent Platform
Nexent is a no-code platform for automatically generating enterprise‑grade AI agents using Harness Engineering principles.
★ 4,535 · PythonCOMMAND CODE AI
AI assistant that generates and executes code from natural language commands.
★ 4,243HARNESS AGENT TEAM
The Harness project creates a meta‑skill that forms specialized agent teams and generates the needed skills for them.
★ 3,673 · HTMLPENGUIN-HARNESS - DESKTOP AGENT FACTORY
An automatic AI agent factory right on your desktop. A self-sufficient harness that improves itself.
★ 3,240 · TypeScriptGOCLAW: Go AI Agents Instantly
GoClaw is OpenClaw rewritten in Go with multi-user isolation and 5-level security for scalable deployment of AI-agent teams.
★ 3,188 · GoLLM-Space — Prototype Agents Easily
Desktop application for developing and testing LLM agents with deep control of each step.
★ 2,130 · TypeScriptLOU SHANG - AI CODING AGENT
A universal AI agent on Python that combines multiple LLMs and tools for automating coding.
★ 2,091 · PythonLONG AI HARNESS FOR WORK
Run AI agents in desktop applications and CLI for hours, preserving task state and ensuring reliable progress of complex workflows.
★ 1,873 · PythonHOPE-AGENT: SMART AI AGENT FOR DESKTOP
Hope-agent — a cross-platform AI agent in Rust with long-term memory, autonomous goal execution, and dynamic agent orchestration. Supports headless launch on NAS or in th
★ 1,857 · RustHybrid Review Tool
A tool for automatic code review that combines deterministic pipelines with an LLM agent, providing inline comments and using a ready set of rules to detect NPE, thread‑s
★ 1,792 · GoMemsearch: Memory for AI Agents
A resilient unified memory layer for all your AI agents (Claude Code, Codex, etc.), built on Markdown and Milvus.
★ 1,732 · PythonPUPPYONE - AI CONTEXT DRIVER
A platform for managing AI-agent contexts, allowing easy data connection and improving their responses.
★ 1,604 · TypeScriptTOP-100 AI AGENT HARNESSES
A weekly updated list of 100+ top harnesses for AI agents with an MCP server and ready-to-use recommendation formats.
★ 1,523 · Pythonawesome-deepseek-harness - SPEEDING WORK WITH DEEPSEEK
Ecosystem of plugins and tools for DeepSeek Harness: ready-made solutions from dsh-external/hub and the public topic dsh-plugin.
★ 1,370 · PythonCONTEXT MEMORY FOR AI AGENTS
Puppyone-cloud is a context engine for AI agents. It provides persistent storage, versioning, and instant retrieval of relevant context for LLMs. Simplifies building agen
★ 1,299 · PythonSelf‑Evolving Data Ontology
Plugin that builds and continuously updates an ontology layer for data agents, enabling Claude Code/Codex to reason over evolving knowledge.
★ 1,213 · PythonFLOCK: MULTI-AGENT PLATFORM ON RUST
Desktop framework for multi-agent systems built with Rust, Tauri, and React, with LangGraph support.
★ 1,077 · RustMODSEARCH - COMPLETELY FREE SEARCH
modsearch is a free web‑search plugin for DeepSeek Harness that lets any LLM obtain structured JSON data from the web and X without registration or an API key.
★ 989 · TypeScriptCLAW-EVAL - LLM Agent Evaluation
Claw-Eval is a suite of tests for evaluating LLM agents, with all tasks human-verified.
★ 934 · PythonCHORUS: AI COLLAB AGENT
Framework for efficient human-AI agent interaction during development, inspired by AI-DLC.
★ 909 · TypeScriptFABLIZE CODING PLUGIN
Fablize — a plugin for Claude Code that makes Opus behave like Fable: it enforces strict completeness, provides proofs, and treats verification as a procedure.
★ 892 · ShellGORAVEN: Team Agents
Open-source AI-agent platform that reads files, runs code, and calls APIs to deliver ready results for the team.
★ 849 · GoMCP CLIENT FOR LOCAL LLM
TUI client for Ollama with support for all MCP primitives, agent mode, multi-server capability, and streaming output. 749 ⭐
★ 836 · PythonJAVIS OS: AGENT PLATFORM ON PYTHON
Javis OS — platform for managing AI agents: task orchestration, execution optimization and flexible configuration. Written in Python, supports extensions via API and CLI.
★ 818 · PythonDIGITAL AGENT SYRENE
Cyrene-Agent — an open‑source desktop AI agent with Cyrene’s persona, built on the Cyrene_Harness framework. It blends lifelike companion chat with practical features: co
★ 801 · TypeScriptAEON: Autonomous Agent Framework
AEON is a framework for fully autonomous AI agents without approval loops or constant supervision. Set up once and forget.
★ 793 · TypeScriptLong-Horizon Agent Framework
Cayu is a Python framework for building domain-specific long-horizon agents with a built-in durable runtime for reliable execution.
★ 791 · PythonSoduWork: ENGINE FOR AI AGENTS
AI-native platform for managing agent teams. Supports multi-harness approach, workflow orchestration, and self-hosted deployment.
★ 774 · JavaScriptCODEAF: FACTORY OF OPEN MODELS!!
CodeAF — open-source factory for creating and managing AI agents in Go. Enables rapid assembling, testing, and deploying the agent fleets for coding and other tasks.
★ 744 · GoCUGA-AGENT — Universal Agent
An open framework for building AI agents with web/API integration support, OpenAPI/MCP, and advanced reasoning modes.
★ 742 · PythonLAZYMIND AI-ENVIRONMENT FOR KNOWLEDGE
LazyMind is an AI skill runtime for knowledge-intensive work, giving you full control. It lets you fully manage search, generation, and application of information.
★ 718 · GoLocal Claude Video Studio
Generate videos step‑by‑step with Claude, approving each frame on your own machine using your Claude Code or API key.
★ 702 · JavaScriptDSH-COST-METER: TRACKING EXPENSES
The dsh-cost-meter plugin for DeepSeek Harness tracks the session and daily cost, budget, and history of DeepSeek Harness. Includes the token map,peak/off-peak pricing
★ 699 · JavaScriptTIMON — AI AGENT ORCHESTRATOR ON LOCAL MACHINE
Timon manages a team of AI agents on your computer using existing CLI subscriptions without token billing. The orchestrator distributes tasks among coder, reviewer, merge
★ 615 · TypeScriptAGENTBOX: PARALLEL AGENT LAUNCH
Launch multiple AI agents in isolated virtual machines with one command — locally or in the cloud.
★ 582 · TypeScriptRATEL SMART MEMORY FOR AGENTS
Ratel is a Rust framework for AI‑agent context engineering: it cuts token usage by ~80% and provides in‑process BM25 plus semantic search without a vector DB.
★ 563 · RustYOUR TEAM OF AI BOTS IN ONE BINARY
Self-hosted solution for AI agent team: spaces, all accounts in one place, task handoffs, approvals and routines. Written in Rust + React. Alternative to Grok Bot, Claude
★ 556 · RustMOBIUS: RUST FRAMEWORK FOR AGENTS
Möbius is a compact Rust framework for building code-writing agents. Frontend-agnostic and works with any LLM. Already gained 300 GitHub stars.
★ 547 · RustSECURE SANDBOX FOR AI AGENTS
Box isolates AI agents, using OS isolation and default‑deny Dogwood policies. It injects credentials from a secure store without exposing them to the agent, and restricts
★ 546 · RustPANTHEONOS: Data Science Agent
PantheonOS is a modular framework for building distributed AI agents, simplifying data pipelines and experiments.
★ 496 · PythonEvent-Sourced Actor Framework
Build resilient TypeScript applications using composable actors backed by an immutable event log for state reconstruction and replay.
★ 474 · TypeScriptALWAYS-ACCOMPANY - AI PARTNER FOR CODE
The always-accompany project creates an AI agent with shared memory and context for chat, code, and collaboration — like in science fiction.
★ 460 · JavaScriptLLM AGENT HARNESS OVERVIEW
Overview of over 110 papers and 23 systems for building agents for large language models.
★ 437AI AGENTS IN SAFE
SAW — AI-agent framework on SAFe for multi-agent processes in any domain.
★ 430 · ShellAZURE OPENAI LLM NOTES - MONTHLY
A curated collection of resources on Azure OpenAI, LLM, RAG, and agents with monthly updates. Ideal for quick start and deep dive.
★ 422 · PythonNew projects on this topic in Telegram
Telegram →