# PrimeIntellect-ai/prime-agent

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

Repository: https://github.com/PrimeIntellect-ai/prime-agent
Canonical: https://ross.abutalabs.com/products/prime-agent
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T22:36:41+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 8
- inputs: {"age_days": 118, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 45}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18642, forks 2008 (observed 2026-08-28T04:11:26.820035+00:00)

## What it is
Prime Agent is an open-source coding and research agent built around Recursive Language Models (RLM) and a Continual Harness that stores prompts, memories, and subagent specs as durable state. It runs a persistent Python REPL as the core tool, enabling programmatic tool use, file/shell operations, and recursive subagent spawning for long-running autonomous tasks.

## Use cases
- run long-running autonomous coding tasks
- spawn parallel subagents for background work
- build a self-improving agent harness with persistent memory
- automate research and coding workflows from a terminal
- manage context as variables in a persistent REPL
- delegate recursive subagent calls programmatically

## When to choose
- you want an open-source autonomous coding agent with durable memory and skills
- you need programmatic subagent orchestration for parallel or background tasks
- you want a REPL-driven agent where everything is code
- you're experimenting with Recursive Language Model architectures

## When to avoid
- you need a simple one-shot code completion assistant
- you want a GUI-first agent experience
- you're not comfortable with agents executing shell commands and code autonomously

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, rag, developer-tools, cli
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, cross-platform
- tags: coding-agent, recursive-language-model, self-improving, subagents, persistent-repl, autonomous-agents, ai-agents, automation, nodejs

## Member repositories
- PrimeIntellect-ai/prime-agent (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.820035+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:01:20.874006+00:00, confidence not recorded.
  - readme: https://github.com/PrimeIntellect-ai/prime-agent (fetched 2026-08-28T04:11:26.820035+00:00, sha 1aae69b48b64)
- Data as of 2026-08-30T08:39:29.467469+00:00.