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.
☆894Aug 3, 2026Updated last month
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.☆208Sep 10, 2026Updated last week
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,217Mar 26, 2026Updated 5 months ago
- A curated list of papers and resources based on the survey "Code as Agent Harness"☆702May 20, 2026Updated 4 months ago
- Reference code for the Meta-Harness paper.☆1,590Sep 11, 2026Updated last week
- AutoHarness: Automated Harness Engineering for AI Agents☆377Apr 2, 2026Updated 5 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ICML'26] MemEvolve & EvolveLab☆270May 5, 2026Updated 4 months ago
- The official GitHub page for the paper "Agent Systems with Harness Engineering"☆199May 25, 2026Updated 3 months ago
- ☆90Jun 19, 2026Updated 3 months ago
- Framework for evaluating and improving agents☆5,411Updated this week
- Awesome list and survey website for agents in the era of experience☆265Sep 11, 2026Updated last week
- [ICML 2026] InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning☆34May 25, 2026Updated 3 months ago
- An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.☆1,774Updated this week
- Offical implementation of "Life-Harness"☆222Updated this week
- RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past traje…☆56Jun 12, 2026Updated 3 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.
- OpenClaw-RL: Train any agent simply by talking☆5,691May 23, 2026Updated 3 months ago
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆978May 17, 2026Updated 4 months ago
- ☆116Dec 5, 2025Updated 9 months ago
- [EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"☆375Aug 12, 2026Updated last month
- Qwen-AgentWorld: Language World Models for General Agents☆1,013Jul 20, 2026Updated 2 months ago
- Self-referential self-improving agents that can optimize for any computable task☆2,747Jul 31, 2026Updated last month
- [ICML 2026] Meta Context Engineering via Agentic Skill Evolution☆170May 4, 2026Updated 4 months ago
- CL-bench: A Benchmark for Context Learning☆583May 12, 2026Updated 4 months ago
- ☆1,324Oct 15, 2025Updated 11 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆411Apr 30, 2026Updated 4 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,590Jul 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…☆17,262Sep 5, 2026Updated 2 weeks ago
- This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language☆99Jul 22, 2026Updated last month
- The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".☆197Sep 3, 2026Updated 2 weeks ago
- slime is an LLM post-training framework for RL Scaling.☆8,507Updated this week
- ☆33Apr 29, 2026Updated 4 months ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,803Aug 23, 2026Updated 3 weeks ago
- MemoHarness: Agent Harnesses That Learn from Experience☆98Jul 30, 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.
- EdgeBench: Unveiling scaling laws of learning from real-world environments☆450Sep 9, 2026Updated last week
- ☆106Mar 13, 2026Updated 6 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,492Updated this week
- Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework☆354Jan 17, 2026Updated 8 months ago
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents☆579May 23, 2026Updated 3 months ago
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆1,108May 12, 2026Updated 4 months ago
- "OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"☆15,803Jun 4, 2026Updated 3 months ago