← νŠΈλ Œλ”©

Tangerine IndexλŠ” ChatGPT 이후 λ‚˜μ˜¨ ν”„λ‘œλ•νŠΈμ™€ μ‚¬λžŒλ“€μ˜ λ°˜μ‘μ„ μ‹£μŠ΅λ‹ˆλ‹€.

GPTSwarm

github.com

🐝 The First Self-Improving agents with RL / Prompting Optimization

μ˜€ν”ˆμ†ŒμŠ€

github.com λ°©λ¬Έμ™ΈλΆ€ μ‚¬μ΄νŠΈGitHub1,068 μŠ€νƒ€μ™ΈλΆ€ μ‚¬μ΄νŠΈ

λ°˜μ‘ (1)

λΉ„μŠ·ν•œ ν”„λ‘œλ•νŠΈ

μ„€λͺ…이 λΉ„μŠ·ν•œ 순

  1. prime-rl

    Agentic RL Training at Scale

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 2,224

  2. letta-code

    Agents that self-improve with experience

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 3,797

  3. Microagents

    Agents capable of self-editing their prompts / Python code

    github.comμ˜€ν”ˆμ†ŒμŠ€λ°˜μ‘ 2개졜근 λ°˜μ‘

    Hacker News
    221점
    GitHub
    μŠ€νƒ€ 821

  4. reef

    Infrastructure for continually self‑improving agents

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 7,782

  5. OpenManus-RL

    A live stream development of RL tunning for LLM agents

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 4,174