PrimeIntellect-ai/prime-agent
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
About the project
An open-source coding and research agent in Rust with a persistent Python REPL, recursive subagents, and self-improving harness state for long-running autonomous tasks.
Useful for
- Run the agent in a repository to complete a long autonomous task while preserving progress across sessions
- Spawn subagents via rlm.spawn to work on parts of a codebase in parallel
- Use /refine to persist working patterns as skills and memories for future sessions
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 11 stars so far today, about 26 expected by the end of the day.
- GitHub Trending Rust today: #6, +51 stars.
- About 9 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 21,441
- Today
- 11 · ≈ 26 by evening
- Forks
- 2,362
- Issues and pull requests
- 2,871
- Watchers
- 86
- Language
- Rust
- Latest release
- v0.9.9-beta.11 · October 1, 2026
- Created
- May 8, 2026
- Last push
- October 1, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- October 1, 2026GitHub Trending Rust today: #6, +51 stars
Similar by description
-
1.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.
-
2.4
bytedance/deer-flow
Open-source harness for long-horizon AI agent tasks: orchestrates sub-agents, memory, sandboxes and skills for research, coding and content creation.