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.
☆954Oct 30, 2026Updated this 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:
- Official code for Meta-Harness (2603.28052)☆1,731Oct 2, 2026Updated 3 weeks ago
- Rethinking the Evaluation of Harness Evolution for Agents☆50Oct 15, 2026Updated 2 weeks ago
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆22Aug 4, 2026Updated 2 months ago
- Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)☆1,245Mar 26, 2026Updated 7 months ago
- This is the official repository for the paper From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws☆26Jul 2, 2026Updated 3 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.☆179Aug 25, 2026Updated 2 months ago
- [EMNLP'26 Oral] HarnessForge☆32Sep 28, 2026Updated last month
- A curated list of papers and resources based on the survey "Code as Agent Harness"☆752May 20, 2026Updated 5 months ago
- The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".☆836Aug 22, 2026Updated 2 months ago
- Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.☆866Sep 17, 2026Updated last month
- [ICML'26] MemEvolve & EvolveLab☆286May 5, 2026Updated 5 months ago
- Framework for evaluating and improving agents☆6,667Updated this week
- The official GitHub page for the paper "Agent Systems with Harness Engineering"☆228May 25, 2026Updated 5 months ago
- Awesome list and survey website for agents in the era of experience☆292Oct 23, 2026Updated last week
- 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.
- [NeurIPS'26] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning☆1,024Sep 25, 2026Updated last month
- SPADE: Self-Play in Adaptive Synthetic Executable Environments☆126Aug 26, 2026Updated 2 months ago
- ☆97Jun 19, 2026Updated 4 months ago
- ☆339Aug 11, 2026Updated 2 months ago
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆611Oct 2, 2026Updated 3 weeks ago
- Self-referential self-improving agents that can optimize for any computable task☆2,853Jul 31, 2026Updated 3 months ago
- An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.☆1,893Oct 7, 2026Updated 3 weeks ago
- RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past traje…☆67Jun 12, 2026Updated 4 months ago
- JIT-Agent☆570Aug 27, 2026Updated 2 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.
- HarnessX is a harness foundry: forge any number of agent harnesses from reusable processors and bundles, pair each with any model, and ev…☆504Oct 23, 2026Updated last week
- AutoHarness: Automated Harness Engineering for AI Agents☆464Apr 2, 2026Updated 6 months ago
- ☆137Jul 2, 2026Updated 3 months ago
- EdgeBench: Unveiling scaling laws of learning from real-world environments☆474Updated this week
- ☆437Apr 30, 2026Updated 6 months ago
- slime is an LLM training framework for RL Scaling.☆8,770Updated this week
- MemoHarness: Agent Harnesses That Learn from Experience☆115Sep 26, 2026Updated last month
- [ICML 2026] Meta Context Engineering via Agentic Skill Evolution☆183May 4, 2026Updated 5 months ago
- A curated list for Self-Improvement in Foundation Model Based Agentic Systems.☆599Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Configurable inference harness for long-horizon agentic search: 6 agent families, 5 context-management strategies, page memory, 3 multi-a…☆11May 27, 2026Updated 5 months ago
- Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and mu…☆1,110Oct 19, 2026Updated last week
- OpenClaw-RL: Train any agent simply by talking☆5,744May 23, 2026Updated 5 months ago
- 🐧 Unified and Stable RSI Platform☆3,078Updated this week
- Qwen-AgentWorld: Language World Models for General Agents☆1,036Jul 20, 2026Updated 3 months ago
- ☆1,345Oct 15, 2025Updated last year
- Optimize prompts, code, and more with AI-powered Reflective Optimization☆7,218Updated this week