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.
☆813Aug 3, 2026Updated last week
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.☆194Aug 3, 2026Updated last week
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,167Mar 26, 2026Updated 4 months ago
- Reference code for the Meta-Harness paper.☆1,389Jul 11, 2026Updated 3 weeks ago
- A curated list of papers and resources based on the survey "Code as Agent Harness"☆631May 20, 2026Updated 2 months ago
- AutoHarness: Automated Harness Engineering for AI Agents☆367Apr 2, 2026Updated 4 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- The official GitHub page for the paper "Agent Systems with Harness Engineering"☆168May 25, 2026Updated 2 months ago
- [ICML'26] MemEvolve & EvolveLab☆258May 5, 2026Updated 3 months ago
- ☆86Jun 19, 2026Updated last month
- Awesome list and survey website for agents in the era of experience☆210Updated this week
- Framework for evaluating and improving agents☆4,076Updated this week
- [ICML 2026] InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning☆34May 25, 2026Updated 2 months ago
- An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.☆1,580Jun 21, 2026Updated last month
- RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past traje…☆48Jun 12, 2026Updated last month
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆936May 17, 2026Updated 2 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.
- ☆116Dec 5, 2025Updated 8 months ago
- OpenClaw-RL: Train any agent simply by talking☆5,626May 23, 2026Updated 2 months ago
- Qwen-AgentWorld: Language World Models for General Agents☆936Jul 20, 2026Updated 3 weeks ago
- [ICML 2026] Meta Context Engineering via Agentic Skill Evolution☆153May 4, 2026Updated 3 months ago
- Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"☆361Updated this week
- CL-bench: A Benchmark for Context Learning☆576May 12, 2026Updated 2 months ago
- ☆368Apr 30, 2026Updated 3 months ago
- ☆1,278Oct 15, 2025Updated 9 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,534Jul 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.
- Self-referential self-improving agents that can optimize for any computable task☆2,671Jul 31, 2026Updated last week
- A reproducible framework for benchmarking LLM native forecasting via knowledge cutoff and temporal masking.☆36Jun 17, 2026Updated last month
- This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language☆93Jul 22, 2026Updated 2 weeks ago
- SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, va…☆15,846Updated this week
- MemoHarness: Agent Harnesses That Learn from Experience☆85Jul 30, 2026Updated last week
- Maka — local-first AI desktop assistant☆1,316Updated this week
- slime is an LLM post-training framework for RL Scaling.☆7,832Updated this week
- ☆31Apr 29, 2026Updated 3 months ago
- The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".☆182Feb 12, 2026Updated 5 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- EdgeBench: Unveiling scaling laws of learning from real-world environments☆415Jul 17, 2026Updated 3 weeks ago
- ☆105Mar 13, 2026Updated 4 months ago
- Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework☆337Jan 17, 2026Updated 6 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,900Updated this week
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents☆560May 23, 2026Updated 2 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…☆6,357Aug 3, 2026Updated last week
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,765Jul 24, 2026Updated 2 weeks ago