Prime Agent: Open-Source Self-Improving RLM Agent for Coding, 2,293 Stars in 24h
Roger_M_Taylor · x · 2026-08-09
PrimeIntellect has open-sourced Prime Agent, an agent for coding and long-running autonomous tasks. It is built on a Recursive Language Model (RLM) that treats context as variables and tools as function calls, with a continual harness for storing prompts, memories, and skills. The project gained 2,293 stars in 24 hours, totaling 7,568 stars on GitHub.
Related event: Prime Intellect Open-Sources Self-Improving Prime Agent(3 posts)→
More from coding & agent
- DIRECT: retrieval-based next-question suggestions for conversational agents — burkov · 2026-10-16
- Claude Code and Codex now autocomplete the user's next action — tokenbender · 2026-10-16
- Hermes Agent ships official Reverse Engineer Anything plugin with one-command setup — Teknium · 2026-10-16
- MLExpert: 35B MoE Agent Trained to Autonomously Handle Machine Learning Engineering — Shangheng Du · 2026-10-16
- Cowork-Gym: Alibaba Synthesizes 64.9K Agent Work Environments, Boosting Qwen by 8.7 Points — Anni Zou · 2026-10-16
- MMSearch-OPD: Joint RL and On-Policy Distillation for Long-Horizon Multimodal Search Agents — PekingUniversity · 2026-10-16