Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.
☆915Aug 3, 2026Updated 2 months ago
Alternatives and similar repositories for agentic-harness-engineering
Users that are interested in agentic-harness-engineering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NexAU (AU for Agent Universe), a general-purpose agent framework for building intelligent agents with tool capabilities.☆211Sep 10, 2026Updated last month
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,231Mar 26, 2026Updated 6 months ago
- A curated list of papers and resources based on the survey "Code as Agent Harness"☆714May 20, 2026Updated 4 months ago
- Official code for Meta-Harness (2603.28052)☆1,643Oct 2, 2026Updated last week
- AutoHarness: Automated Harness Engineering for AI Agents☆435Apr 2, 2026Updated 6 months ago
- 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.
- [ICML'26] MemEvolve & EvolveLab☆278May 5, 2026Updated 5 months ago
- The official GitHub page for the paper "Agent Systems with Harness Engineering"☆212May 25, 2026Updated 4 months ago
- ☆91Jun 19, 2026Updated 3 months ago
- Framework for evaluating and improving agents☆5,951Updated this week
- Awesome list and survey website for agents in the era of experience☆277Updated this week
- [ICML 2026] InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning☆34May 25, 2026Updated 4 months ago
- Offical implementation of "Life-Harness"☆224Updated this week
- An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.☆1,839Updated this week
- RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past traje…☆58Jun 12, 2026Updated 3 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- OpenClaw-RL: Train any agent simply by talking☆5,717May 23, 2026Updated 4 months ago
- [NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆1,002Sep 25, 2026Updated 2 weeks ago
- ☆116Dec 5, 2025Updated 10 months ago
- [EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"☆379Aug 12, 2026Updated last month
- Qwen-AgentWorld: Language World Models for General Agents☆1,028Jul 20, 2026Updated 2 months ago
- Self-referential self-improving agents that can optimize for any computable task☆2,790Jul 31, 2026Updated 2 months ago
- [ICML 2026] Meta Context Engineering via Agentic Skill Evolution☆176May 4, 2026Updated 5 months ago
- CL-bench: A Benchmark for Context Learning☆583May 12, 2026Updated 4 months ago
- ☆1,329Oct 15, 2025Updated 11 months ago
- 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.
- ☆425Apr 30, 2026Updated 5 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,600Jul 11, 2026Updated 2 months ago
- SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, va…☆18,159Updated this week
- Reproducible LLM forecasting with a fixed 300-question benchmark, Score and time-masked retrieval.☆37Updated this week
- This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language☆100Jul 22, 2026Updated 2 months ago
- The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".☆199Sep 3, 2026Updated last month
- slime is an LLM post-training framework for RL Scaling.☆8,615Updated this week
- ☆33Apr 29, 2026Updated 5 months ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,818Aug 23, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- MemoHarness: Agent Harnesses That Learn from Experience☆106Sep 26, 2026Updated 2 weeks ago
- EdgeBench: Unveiling scaling laws of learning from real-world environments☆465Sep 20, 2026Updated 2 weeks ago
- ☆106Mar 13, 2026Updated 6 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,805Updated this week
- Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework☆355Jan 17, 2026Updated 8 months ago
- The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—b…☆8,343Updated this week
- [NeurIPS'26] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents☆581Oct 1, 2026Updated last week