Reference code for the Meta-Harness paper.
☆1,496Jul 11, 2026Updated last month
Alternatives and similar repositories for meta-harness
Users that are interested in meta-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,196Mar 26, 2026Updated 5 months ago
- Meta Harness Implementation☆160Updated this week
- Hierarchal Agent Loop Optimizer☆1,158Aug 19, 2026Updated 2 weeks ago
- Production-grade DSPy 3.2.x agent skills + validated end-to-end examples for Claude Code and Codex CLI — fundamentals, evaluation, GEPA, …☆277Jun 20, 2026Updated 2 months ago
- Optimize prompts, code, and more with AI-powered Reflective Optimization☆6,358Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Method for Long Context RLMs using verifiable Lambda Calculus☆305Apr 24, 2026Updated 4 months ago
- The open-source agent-serving project☆482Jul 16, 2026Updated last month
- Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, output…☆430Aug 5, 2026Updated 3 weeks ago
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆5,572Aug 26, 2026Updated last week
- A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).☆100Apr 28, 2026Updated 4 months ago
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆771Aug 22, 2026Updated last week
- autonomous harness engineering☆4,567Apr 3, 2026Updated 4 months ago
- context-efficient terminal agent powered by an RLM☆61Feb 7, 2026Updated 6 months ago
- An implementation of a Meta Harness for Hermes.☆113Jul 11, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A feature rich implementation of Recursive Language Models, with ACP integration, REPL tool support, structured IO, advanced visualizatio…☆474Aug 24, 2026Updated last week
- ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA☆5,222Jun 17, 2026Updated 2 months ago
- Autonomous experiment loop extension for pi☆7,970Updated this week
- turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel…☆1,439Jul 17, 2026Updated last month
- ☆112Jun 10, 2026Updated 2 months ago
- a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task☆1,289Updated this week
- Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-h…☆866Aug 3, 2026Updated last month
- Evolve your language agent with Agentic Context Engineering (ACE)☆1,293Aug 24, 2026Updated last week
- Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and mu…☆942Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against…☆534Jul 8, 2026Updated last month
- LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training.…☆3,067Aug 20, 2026Updated last week
- Self-referential self-improving agents that can optimize for any computable task☆2,703Jul 31, 2026Updated last month
- A benchmark for evaluating AI agents on frontier ultra long-horizon auto research tasks.☆164Updated this week
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,688Updated this week
- Agentic RLM workbench on DSPy 3.3: sandboxed code execution, live operator streaming over SSE, durable sessions & artifacts, terminal-fir…☆51Updated this week
- Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding ag…☆26,999Aug 19, 2026Updated 2 weeks ago
- A sandboxed Python runtime for AI agents, written in Rust.☆145Apr 21, 2026Updated 4 months ago
- Browser Harness | Self-healing harness that enables LLMs to complete any task.☆17,324Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every q…☆2,259Jul 10, 2026Updated last month
- DSPy: The framework for programming—not prompting—language models☆37,727Updated this week
- AI agents running research on single-GPU nanochat training automatically☆95,118Mar 26, 2026Updated 5 months ago
- The World's First Virtual Terminal for AI Agents☆3,597Updated this week
- A recursive coding agent inpired by RLMs☆386Jun 22, 2026Updated 2 months ago
- Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orches…☆49Apr 18, 2026Updated 4 months ago
- ☆39Apr 15, 2026Updated 4 months ago