PrimeIntellect-ai/prime-agent

▲ 67 stars today★ 22,795⑂ 2,530

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

About PrimeIntellect-ai/prime-agent

PrimeIntellect-ai/prime-agent is an open-source project on GitHub, mainly written in Rust. A self-improving RLM agent for coding workflows and long-running autonomous tasks. It currently holds 22,795 stars and 2,530 forks with 51 open issues, and was last pushed on 2026-11-17 (repository created 2026-05-08).

Project Overview

Git Homed tracks it on the Today's Trending board, currently at rank #67 with 67 new stars today.

GitHub Repository Details

Repository PrimeIntellect-ai/prime-agent · default branch main · size 120617 KB · watchers 85 · source: GitHub REST API and repository README

README

https://github.com/PrimeIntellect-ai/prime-agent/blob/HEAD/Prime Intellect

Prime Agent: A Self-Improving RLM Harness

Documentation • Verifiers • PRIME-RL

https://github.com/PrimeIntellect-ai/prime-agent/blob/HEAD/CI https://github.com/PrimeIntellect-ai/prime-agent/blob/HEAD/arXiv

https://github.com/PrimeIntellect-ai/prime-agent/blob/HEAD/PrimeIntellect-ai%2Fprime-agent | Trendshift

Prime Agent is an open-source coding and research agent for general and long-running work. It is designed around two core abstractions:

Install

Install the latest stable version with the one-command installer:

curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh

On Windows, install from PowerShell:

irm https://app.primeintellect.ai/prime-agent/install.ps1 | iex

The Windows installer downloads the latest stable Windows x64 build and verifies its checksum before installation.

Why Prime Agent

Prime Agent combines a persistent Python control environment with durable harness state, so useful working context and reusable operating patterns can outlive a single chat window.

Terminal program status (OSC 7501)

Terminals that support OSC 7501 (the Program Status Protocol, such as Rex) can show what Prime Agent is doing in another tab or window. Prime Agent asks the terminal once at startup whether it supports the protocol, and writes a report only when the terminal answers. Terminals that do not answer get nothing new.

A chat reports working for the whole agent run (including tool steps and a pending provider retry), done when the run ends normally, error when it fails for good, and idle at rest or after an interrupt. On exit Prime Agent sends nothing: the terminal keeps the last record, as the protocol asks.

Getting Started

Start Prime Agent from the repository or directory you want it to work in:

cd /path/to/project
prime-agent

On first launch, run /login to choose a subscription or API-key provider. Prime Agent works in the current directory and can run commands and modify files there. Use a disposable clone, clean worktree, or another checkpoint you can inspect and restore.

[!WARNING]
Prime Agent executes model-generated Python and project commands with your user permissions. Its worker and kernel processes improve lifecycle isolation and recovery; they are not a security sandbox. Review changes and use trusted repositories, instructions, and skills only. Run untrusted code or instructions in an external sandbox or restricted environment.

Useful commands:

prime-agent agents                   # Browse running, idle, and saved sessions
prime-agent attach            # Reattach to a running session
prime-agent --resume [path|id]       # Browse sessions or resume one directly
prime-agent status                   # Inspect background service state
prime-agent doctor [--fix]           # Inspect or repair background services
prime-agent update [--force]         # Update Prime Agent
prime-agent shutdown [--force]       # Stop every agent, worker, and background service

Built for Long-Running Work

Prime Agent is built for long-running work, especially for evaluations in research. These features are available in the TUI, and when run autonomously.

Contributing

Start with a GitHub Discussion for general questions, bug reports, and feature requests. Maintainers promote accepted work into Issues, and pull requests are reviewed from maintainers and vouched contributors.

License

Prime Agent is fully open source and released under the MIT License.

Citation

If you use this codebase in your research, please cite Prime Agent:

@article{karten2026prime,
  title={Prime Agent: A Self-Improving RLM Harness},
  author={Karten, Seth and Zhang, Alex L. and Thomas, Kevin and Müller, Sebastian and Bakouch, Elie and Auras, Daniel and Senghaas, Mika and Obeid, Fares and Dunas, Konstantin and Hagemann, Johannes and Jaghouar, Sami},
  journal={arXiv preprint arXiv:2608.23552},
  year={2026}
}

Available at https://arxiv.org/abs/2608.23552.

GitHub Stars & Activity

22,795Stars
2,530Forks
51Open issues
RustLanguage

GitHub Popularity

GitHub stars22,795
Forks2,530
Open issues51
Primary languageRust
LicenseNOASSERTION
Stars gained today67
Created2026-05-08
Last pushed2026-11-17

Trending History

Daily boardrank #67 · ▲ 67 stars

Related GitHub Projects

1

farion1231 / cc-switch

Rust★ 155,112⑂ 10,154▲ 312 stars
→
2

pbakaus / impeccable

Rust★ 111,729⑂ 6,673▲ 693 stars
→
3

rustfs / rustfs

Rust★ 36,197⑂ 1,679▲ 55 stars
→
4

t8y2 / dbx

Rust★ 30,593⑂ 2,785▲ 101 stars
→
5

anomalyco / hex

Rust★ 7,199⑂ 469▲ 198 stars
→
6

NVIDIA-NeMo / Switchyard

Rust★ 3,616⑂ 374▲ 41 stars
→
7

BurntSushi / jiff

Rust★ 3,116⑂ 141▲ 61 stars
→
8

antithesishq / bombadil

Rust★ 2,467⑂ 94▲ 419 stars
→

More Trending Repositories