DSPy
stanfordnlp/dspy
Programming, not prompting: optimize the whole pipeline.
DSPy introduced programming models for LLM pipelines — declarative modules whose prompts and weights are optimized against metrics. Its optimizer-first philosophy reshaped how production harnesses treat prompts.
In the news
First 'Harness Engineering' survey lands on arXiv
'Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents' surveys the field — loops, tool interfaces, context management, memory and recovery — giving the emerging discipline its first comprehensive academic map.
HarnessTax: harness choice swings agent cost more than model choice
Arena.ai's HarnessTax study tests 21 model–harness combinations across Claude Code, Codex CLI and Pi, finding harness choice can significantly change cost even at similar task success rates. Weeks earlier, SWE-bench Pro analysis showed swapping harnesses moved pass@1 more than model upgrades (23%→52% on GLM-5.2) — and that harness rankings barely transfer across models.
Related projects
OpenClaw
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
OpenClaw (born as Clawdbot in late 2025) is a self-hosted personal agent that connects your chats, email, browser and terminal into one always-on assistant. Its explosive growth — hundreds of thousands of stars within months — made 'personal agent harness' a mainstream category.
DeepSeek Harness
deepseek-ai/deepseek-harness
Everything is a Plugin — DeepSeek's open agent harness.
DeepSeek Harness is the breakout open-source harness of 2026: an architecture where everything — tools, subagents, even the loop itself — is a plugin. A Desktop app for macOS and Windows followed in October 2026, and the project passed 240k stars in under three months.
AutoGPT
Significant-Gravitas/AutoGPT
The 2023 experiment that started the autonomous agent wave.
AutoGPT gave GPT-4 a loop, a memory and tools and let it run — kicking off the entire autonomous-agent category. Now rebuilt as a platform for building, deploying and continuously improving agents.