Skip to content
repository radar
Agents & Orchestration

🔁Prime Agent

ACTIVE N/A

PrimeIntellect-ai/prime-agent

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

⭐ Very popular: 16k stars, gaining about 2k a week

View on GitHub ↗

repo profile

vintage 2026 launched this year
language TypeScript
license MIT

momentum

total stars 16k
stars added last week +2k
binary downloads 4k total · GitHub releases
commits / week 36 cooling · -34% vs prior mo
contributors 221
release cadence weekly
last activity yesterday

durability

openness permissive
bus factor 2 concentrated
top-author share 49% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

why it's a big deal

  • /refine applies small, evidence-backed updates to its own harness state, never touching the immutable base prompt, a genuinely different answer to “how does an agent improve” than fine-tuning.
  • Reports 95.5% on ARC-AGI-3 with Opus 5, against a 95.4% human expert baseline, on a model that scores far lower in other harnesses.
  • Daemon-backed sessions and direct agent-to-agent messaging point toward agents as long-running processes, not single chat sessions.

under the hood

  • A persistent IPython REPL is the single model-facing tool, files, shell, and subagents all happen through code.
  • Bounded autonomous mode runs within configured turn, token, and time budgets, with user-defined quality gates.
  • Built on Mario Zechner’s pi harness rather than a ground-up TUI, freeing effort for the RLM and Continual Harness layers.

our take from PR#40, 2026-08-12

star history

PR#40 · 15k16k now May 2026Aug 2026
  1. PR#40 15k 2026-08-12
  2. now 16k + 2k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Output and attention are roughly in balance.

+5 understory score output 89 · clout 84
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#40 2026-08-12 on the radar

    the agent that rewrites its own instructions

similar projects

compare these →
  • 🦀 OpenClaw

    24× the stars

    Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

    386k ACTIVE
  • 🥧 pi-mono

    5.6× the stars

    AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

    91k ACTIVE
  • 📎 paperclip

    4.8× the stars

    The open-source app everyone uses to manage agents at work

    78k ACTIVE

comments

Sign in with GitHub to add your blip on Prime Agent.

loading comments…