10 alternatives to prime-agent
primeintellect-ai/prime-agent — A self-improving RLM agent for coding workflows and long-running autonomous tasks. (22,234 stars, MIT, ai, testing, auth).
These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It also serves 1,043 licence-cleared components from primeintellect-ai/prime-agent itself.
| # | Repo | Score | Licence | Stars |
|---|---|---|---|---|
| 1 | mervinpraison/praisonai | 6.1 | MIT | 9,283 |
| 2 | copilotkit/agno | 4.7 | Apache-2.0 | 42,899 |
| 3 | mindsdb/anton | 5.5 | MIT | 757 |
| 4 | can1357/oh-my-pi | 6.2 | MIT | 36,241 |
| 5 | oliveirabruno01/babyagi-asi | 5.6 | MIT | 809 |
| 6 | esengine/deepseek-reasonix | 6.1 | MIT | 35,905 |
| 7 | openai/codex | 6.2 | Apache-2.0 | 130,304 |
| 8 | 1jehuang/jcode | 6.3 | MIT | 21,098 |
| 9 | eumemic/ai-legion | 6.0 | MIT | 1,439 |
| 10 | plandex-ai/plandex | 6.7 | MIT | 15,782 |
The alternatives in detail
-
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, anscore 6.1/10 · MIT permissive · 9,283 stars · 2,392 components · search them
-
The self-improving agent platform
-
self-improving agentscore 5.5/10 · MIT permissive · 757 stars · 170 components · search them
-
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
-
BabyAGI: an Autonomous and Self-Improving agent, or BASIscore 5.6/10 · MIT permissive · 809 stars · 9 components · search them
-
A reliable coding agent for complex software engineering tasks.
-
Lightweight coding agent that runs in your terminalscore 6.2/10 · Apache-2.0 permissive · 130,304 stars · 3,001 components · search them · alternatives
-
High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows
-
An LLM-powered autonomous agent platformscore 6.0/10 · MIT permissive · 1,439 stars · 35 components · search them
-
Open source AI coding agent. Designed for large projects and real world tasks.score 6.7/10 · MIT permissive · 15,782 stars · 314 components · search them
Licence data: JustClaw-It's per-repo licence policy. Is prime-agent still maintained? Check it. Licence details: licence checker. Ranking data from 2026-10-27T23:04:12Z.
Want code like prime-agent without the licence risk? JustClaw-It is an MCP server with 1,449,000+ licence-cleared, quality-scored code components. Search is free; every result carries its licence and attribution.
Remote MCP endpoint: https://justclaw.it.com/mcp (API key auth). Works with Claude Code, Cursor,
Codex, Windsurf and other MCP clients. A one-line CLI installer (@justclaw-it/cli) is coming.