GitHub radar

Prime Agent — self-improving AI coder by Prime Intellect

Prime Agent from Prime Intellect is an open source self-tuning code agent. It iteratively improves its prompts and skills based on previous interactions, so it gets better at the tasks you give it over time.

Prime Agent is a code & research agent created by Prime Intellect, released as open source only 4 months ago and has nearly 18,000 stars! Prime Agent is an IPython persistent environment that lets you execute code, edit files, spawn/interact with parallel subagents, etc., all automatically without your intervention. Its core functionality is self-improvement; each time you use the /refine command, it learns from past experiences and optimizes its supplementary prompts/abilities for future iterations. You can also store frequently used workflows as reusable skills. Lastly, its long running auto mode + periodic heartbeats enable it to continue working on complex research problems for hours while you sleep. Supported platforms: Mac OS X, Linux. Upon first use, you may choose to subscribe to a plan or enter your own OpenAI/Anthropic/etc. API key.

Why a vibe-coder should care

Unlike other agents, Prime Agent remembers things! Each time you use the /refine command, it becomes increasingly proficient at completing the desired tasks. Its long running auto mode + periodic heartbeats enable it to operate while you sleep, tackling complex research problems.

How to install

Copy this and send it to your agent — Claude Code, Codex, any of them:

Install Prime Agent from here: https://github.com/PrimeIntellect-ai/prime-agent — follow the README, run the curl installer, configure the model provider (I have an API key, just ask), run a first task and show me the result.

Runs on a regular laptop with macOS or Linux — a language model key or subscription required.

Open on GitHub