The agentic harness engineering directory
Find everyone building the agent harness layer
The orchestration, memory, tooling, runtimes and evaluation stack that turns raw LLMs into reliable agents — 69 startups, 114 open-source projects, 22 events and 30 news items, in one searchable place.
Companies to know
Cognition
Devin, the AI software engineer, and the Windsurf IDE.
Cognition builds Devin, an autonomous AI software engineer that plans and executes engineering tasks end-to-end, and acquired the Windsurf agentic IDE in 2025. One of the defining startups of the coding-agent wave.
LangChain
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
OpenHands
The open platform for cloud coding agents.
OpenHands (formerly All Hands AI, born from the OpenDevin project) builds the major open-source coding-agent platform — agent canvas, sandboxed execution, SDK and an enterprise control plane — now rebranded under the project's name.
Projects defining the stack
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.
Hermes Agent
NousResearch/hermes-agent
The agent that grows with you.
Nous Research's self-improving personal agent: a learning loop turns experience into reusable skills, builds a persistent user model across sessions, and checkpoints state to disk with rollback — lean enough for a $5 VPS and driven from the chat apps you already use.
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.
Where harness engineers meet
Code with Claude
Anthropic's developer conference for the Claude ecosystem.
OpenAI DevDay
Where OpenAI ships its agent and platform releases.
MLOps World / GenAI Summit
Machine learning in production — now heavily agentic.
Latest in the harness
DeepSeek ships Harness Desktop; the 'everything is a plugin' harness passes 240k stars
DeepSeek releases a macOS and Windows Desktop app for DeepSeek Harness, its open-source agent harness where everything — tools, sub-agents, even the loop — is a plugin. The repo passed 240k stars within three months of its August launch, making it the fastest-growing harness in the field's history.
Best of Agent Harnesses tracks 167 harnesses — and their graveyard
The Best of Agent Harnesses list ranks 167 agent harnesses weekly by capability, autonomy and recovery, ships an MCP server so agents can pick their own harness, and maintains a graveyard that flagged a 268k-star repo for suspected star manipulation. Curation itself becomes harness infrastructure.
Restate raises $20M Series A for agent infrastructure
Restate raises $20M to 'define the infrastructure layer for AI agents and workflows' — its lightweight durable runtime journals every agent step so invocations survive crashes. The round underlines durable execution as the best-funded sub-category of agent infrastructure.
EverMind open-sources Raven — 'the harness of harnesses'
EverMind AI releases Raven, a trusted, persistent, self-evolving multi-agent ecosystem built for recursive self-improvement — agents that modify their own harness under governance. The Show HN thread became a running debate on how much autonomy a harness should hand an agent over itself.
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.