Reference code for the Meta-Harness paper.
☆1,603Sep 11, 2026Updated last week
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)☆1,223Mar 26, 2026Updated 5 months ago
- Meta Harness Implementation☆171Sep 2, 2026Updated 3 weeks ago
- Hierarchal Agent Loop Optimizer☆1,175Sep 8, 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, …☆278Sep 6, 2026Updated 2 weeks ago
- Optimize prompts, code, and more with AI-powered Reflective Optimization☆6,702Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Method for Long Context RLMs using verifiable Lambda Calculus☆308Apr 24, 2026Updated 4 months ago
- Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, output…☆434Sep 8, 2026Updated 2 weeks ago
- General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.☆5,640Aug 26, 2026Updated 3 weeks ago
- A plugin for your agentic framework that optimizes code using the GEPA algorithm (Genetic-Pareto LLM-driven search).☆99Apr 28, 2026Updated 4 months ago
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆802Aug 22, 2026Updated last month
- autonomous harness engineering☆4,572Apr 3, 2026Updated 5 months ago
- context-efficient terminal agent powered by an RLM☆61Feb 7, 2026Updated 7 months ago
- ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA☆5,388Jun 17, 2026Updated 3 months ago
- An implementation of a Meta Harness for Hermes.☆116Jul 11, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A feature rich implementation of Recursive Language Models, with ACP integration, REPL tool support, structured IO, advanced visualizatio…☆476Aug 24, 2026Updated 3 weeks ago
- Autonomous experiment loop extension for pi☆8,102Sep 10, 2026Updated last week
- turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel…☆1,458Jul 17, 2026Updated 2 months ago
- ☆112Jun 10, 2026Updated 3 months ago
- Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and mu…☆1,006Sep 8, 2026Updated 2 weeks ago
- a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task☆1,300Updated this week
- Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-h…☆901Aug 3, 2026Updated last month
- Evolve your language agent with Agentic Context Engineering (ACE)☆1,329Aug 24, 2026Updated 3 weeks ago
- Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against…☆538Sep 16, 2026Updated last 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.
- Self-referential self-improving agents that can optimize for any computable task☆2,755Jul 31, 2026Updated last month
- LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training.…☆3,259Aug 20, 2026Updated last month
- A benchmark for evaluating AI agents on frontier ultra long-horizon auto research tasks.☆165Aug 30, 2026Updated 3 weeks ago
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,766Updated this week
- Recursive AI System☆52Updated this week
- Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding ag…☆27,351Sep 15, 2026Updated last week
- Repository for TRACE: Capability-Targeted Agentic Training☆121Jul 12, 2026Updated 2 months ago
- A self-learning data agent built with systems engineering principles. It grounds answers in 6 layers of context and improves with every q…☆2,268Jul 10, 2026Updated 2 months ago
- DSPy: The framework for programming—not prompting—language models☆38,207Updated 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 sandboxed Python runtime for AI agents, written in Rust.☆146Apr 21, 2026Updated 5 months ago
- Browser Harness | Self-healing harness that enables LLMs to complete any task.☆18,019Sep 12, 2026Updated last week
- The World's First Virtual Terminal for AI Agents☆3,648Updated this week
- AI agents running research on single-GPU nanochat training automatically☆96,553Mar 26, 2026Updated 5 months ago
- AI-Driven Scientific, Algorithmic, and Systems Discovery☆684Sep 14, 2026Updated last week
- A recursive coding agent inpired by RLMs☆390Jun 22, 2026Updated 3 months ago
- Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orches…☆52Apr 18, 2026Updated 5 months ago