Prime Agent

Prime Intellect's self-improving coding and research agent. The **harness** is a recursive language model loop (context as a variable, sub-agents as function calls inside a persistent IPython REPL) plus a Continual Harness that lets the agent create, read, update, and delete its own prompts, skills, memory, and sub-agents mid-run; daemon-backed sessions survive a closed terminal, and autonomous mode runs on turn, token, and time budgets. 95.5% on ARC-AGI-3 with Opus 5; the terminal UI is the shell.

memorymulti-agentclitypescript
Stars
22.5k
Adoption surface
slightly complex
Autonomy
headless
Recovery
resumable
License
✅ open-source
Category
Coding agent products (IDEs, CLIs, full suites)

Repository ↗ Example: YC Paper Club talk (18:00) ↗

Related in Coding agent products (IDEs, CLIs, full suites)

Maintain Prime Agent? Add the badge

Best of Agent Harnesses

Paste this into your README so readers can find the list and see how Prime Agent compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)