exoharness
exoharness.ai · 484 words · saved by 1 readers
exoharness is a minimal architecture for building agents. It separates trusted state, resources, and security from agent-specific logic.
exoharness is a minimal architecture for building agents. It separates trusted infrastructure for state, resources, and security from agent-specific logic that can evolve, stop, resume, and rewind across runs. > write events, not hidden state `rust core` `typescript harnesses` `codex` `claude code` `cursor sdk` `mit` ```exo/live entry exo repl exo repl default executor ~/repo $ exo replattached default agent and conversationaster-meadow-2e0e> examine this code and tell me how to make it faster[ttft 812 ms]assistant: The slow path is rebuilding the prompt view from the full event log…
saved by
related reading
- Executors & Harnesses | exo docsexoharness.ai
- The Harness Playbookstencil.so
- What is an Agent Harness?rubriclabs.com
- Welcome to Learn Harness Engineeringwalkinglabs.github.io
- Harness Engineering for Self-Improvement | Lil'Loglilianweng.github.io
- GitHub - shareAI-lab/learn-claude-code: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1github.com
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- Inside Coding Agentsvpromise.github.io
- Building reliable AI agents · parth sareenparthsareen.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Arjun Virkarjunvirk.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com