PrimeIntellect-ai/prime-agent
Prime Agent is an open-source coding and research agent that uses recursive language models to perform long-running autonomous tasks.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
Prime Agent is an autonomous agent built around the Recursive Language Model (RLM) abstraction, which treats context as variables and tools/subagents as programmatic function calls within a persistent REPL. It employs a Continual Harness that maintains prompts, memories, and skill descriptions as durable state that the agent can refine over time. The project is complemented by verifiers for evaluation and is developed by PrimeIntellect, the same team behind the PRIME-RL open-source RL framework for language models.
Frequently asked
- What is PrimeIntellect-ai/prime-agent?
- Prime Agent is an open-source coding and research agent that uses recursive language models to perform long-running autonomous tasks.
- Is prime-agent open source?
- Yes — PrimeIntellect-ai/prime-agent is open source, released under the MIT license.
- What language is prime-agent written in?
- PrimeIntellect-ai/prime-agent is primarily written in TypeScript.
- How popular is prime-agent?
- PrimeIntellect-ai/prime-agent has 1.2k stars on GitHub.
- Where can I find prime-agent?
- PrimeIntellect-ai/prime-agent is on GitHub at https://github.com/PrimeIntellect-ai/prime-agent.