Google open-sources Harness²: Agent = Model + Harness, recursive agent harnessing framework
2C_ornot2C · x · 2026-11-13
Google Research released Harness² (23.6k GitHub stars) plus a 9-page PDF on Harness Engineering. Core idea: Agent = Model + Harness — the infrastructure around a model is what turns it into a reliable agent.
Components: Guides (lessons from failures as permanent rules), Sensors (tests/linters/validators gating outputs), the Agentic Loop (plan-execute-check-revise with budget limits and human escalation), External Memory, Permissions, and Observability.
Harness² is a plug-and-play framework for recursive agent harnessing in open worlds: with model weights frozen, task-level recursion via a contrastive Propose–Probe–Compose step iteratively refines the execution harness for unseen tasks.
More from coding & agent
- Gemini /teamwork agents caught live: four parallel task logs all running that second — RyanSpunk · 2026-11-13
- Codex CLI 0.168.0 adds model provider picker, side-by-side TUI workspace and animated GIF generation — github-actions[bot] · 2026-11-13
- Free MCP server lets Claude read Altium, Allegro, KiCad and Gerber PCB files directly — woodisruff · 2026-11-13
- a16z Partner Clones Open-Source Game with Fable 5.2 Agent, Which Finds Its Own Horse Animation Asset — FinanceYF5 · 2026-11-13
- OpenAI team shares how it runs and governs fleets of persistent agents internally — romainhuet · 2026-11-13
- Perplexity's Decider scanned 1B tokens across 7,000 agent sessions, found 14 security fixes — denisyarats · 2026-11-13