google-research/harness2
Star history
3 snapshots
| 2026-10-19 | 7859 |
| 2026-10-20 | 15222 |
| 2026-10-25 | 19265 |
- Last 7 days
- +11.4K over 6.1 days
- Last 30 days
- Not enough history (3 snapshots)
- Method
- Differences between stored snapshots. How trends work
About this project
Summary from the repository description
Recursive Agent Harnessing for an Open World A harness is the system around a model that enables it to act as an agent: prompts, tools, memory, skills, orchestration, and more.
Quick start
uv venv --python 3.12 .venvTaken from the project's README. Happylancing Directory does not run or test repository code; review commands before running them.
Why it is in the catalog
Rising on GitHub: created this month, 200+ stars.
- Oct 19GitHub search 路 source
- Oct 20GitHub search
Automated observations
- No repository description provided.
These are estimates from repository metadata, not a review of the code.
More in AI Tools and Agents
- JuliusBrussee/caveman114.9K
馃 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
- NousResearch/hermes-agent256.9K
The agent that grows with you
- earendil-works/pi117.7K
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
- heygen-com/hyperframes71.7K
Write HTML. Render video. Built for agents.
- ggml-org/llama.cpp132.3K
LLM inference in C/C++
- DietrichGebert/ponytail175.7K
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.