InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. OpenAI Academy

    Docs & tutorials

    OpenAI's free courses on AI basics, ChatGPT workflows and agents, Codex and building with the API.

    Hand-checked InnerVault (hand-checked), OpenAI Free courses from OpenAI

  2. agentic-context-engine

    Agents & frameworks

    🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

    Stale GitHub, kayba-ai 2,597 ★Apache-2.0Updated 53 days ago

    git clone https://github.com/kayba-ai/agentic-context-engine.git
  3. agent_learning

    AI repositories

    A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.|从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch

    Stale GitHub, Haozhe-Xing 616 ★MITUpdated 23 days ago

    git clone https://github.com/Haozhe-Xing/agent_learning.git
  4. awesome-ai-agent-learning

    Agents & frameworks

    AI Agent 从入门到实战 - 原创保姆级中文教学,不依赖框架从零构建Agent | 作者:青松与桑叶

    Stale GitHub, 2182977liu-bit 90 ★MITUpdated 6 months ago

    git clone https://github.com/2182977liu-bit/awesome-ai-agent-learning.git
  5. AWorld

    Agents & frameworks

    Search, understand, reproduce, and improve an idea with ease

    Stale GitHub, inclusionAI 1,246 ★MITUpdated 7 days ago

    git clone https://github.com/inclusionAI/AWorld.git
  6. Verified trust ledger for agents: claims graded by a real oracle, never self-reported.

    Stale Official MCP Registry, io.github.trenchsearch Updated 13 days ago 1 note

  7. AgentRecall-X

    MCP servers

    Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

    Indexed GitHub, Goldentrii 377 ★MITUpdated 2 days ago

    git clone https://github.com/Goldentrii/AgentRecall-X.git
  8. dsh-run2skill

    Skills

    Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.

    Stale GitHub, qkycir-123 107 ★MITUpdated 7 days ago

    git clone https://github.com/qkycir-123/dsh-run2skill.git
  9. shikhu

    Skills

    Learn your codebases through self-quizzing and study. Track your knowledge coverage over time.

    Stale GitHub, arjunpatel7 13 ★MITUpdated 10 days ago

    git clone https://github.com/arjunpatel7/shikhu.git
  10. altk-evolve

    MCP servers

    Self improving agents through iterations

    Stale GitHub, AgentToolkit 134 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/AgentToolkit/altk-evolve.git
  11. cass_memory_system

    Agents & frameworks

    Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other

    Stale GitHub, Dicklesworthstone 450 ★Custom licence (see repository)Updated 26 days ago

    git clone https://github.com/Dicklesworthstone/cass_memory_system.git
  12. skillmem

    MCP servers

    Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.

    Stale Official MCP Registry, io.github.liza-studio 9 ★Updated 24 days ago 1 note

    skillmem@0.13.0
  13. agent-apprenticeship

    Agents & frameworks

    The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

    Stale GitHub, ray-r-ren 1,616 ★MITUpdated 37 days ago

    git clone https://github.com/ray-r-ren/agent-apprenticeship.git
  14. BanditDB

    MCP servers

    Persistent decision memory for agents — learns which action works in which context

    Stale Official MCP Registry, com.banditdb Updated 36 days ago 2 notes

    banditdb-python@0.3.1
  15. SuperMemory

    MCP servers

    MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.

    Stale Official MCP Registry, io.github.YashvantHange Updated 5 months ago 1 note

    supermemory-agent@0.2.5
  16. brainbox

    MCP servers

    Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.

    Stale Official MCP Registry, io.github.thebasedcapital Updated 8 months ago 1 note

    brainbox-hebbian@0.1.6
  17. VectorizedMultiAgentSimulator

    Agents & frameworks

    VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

    Stale GitHub, proroklab 621 ★GPL-3.0Updated 6 months ago

    git clone https://github.com/proroklab/VectorizedMultiAgentSimulator.git
  18. Contextloop

    MCP servers

    Team metric definitions for data agents. Learns from corrections, tracks SQL answer accuracy.

    Stale Official MCP Registry, com.getcontextloop Updated 25 days ago 1 note

  19. Brevet

    MCP servers

    Change control for what AI agents learn: humans promote, releases are signed, rules can be recalled

    Stale Official MCP Registry, io.github.BrightbeamAI Updated 40 days ago 1 note

    brevet@0.4.0
  20. Recall

    MCP servers

    Long-term memory for AI agents: learns what is true about each person and answers with sources.

    Stale Official MCP Registry, dev.recallmem Updated 38 days ago 1 note

  21. Hivemind

    MCP servers

    Shared long-term memory for a team's AI agents. What one agent learns, the others can find.

    Indexed Official MCP Registry, io.github.monochrome-muncher Updated today 2 notes

    ghcr.io/monochrome-muncher/hivemind:v2.27.2
  22. Context Vault

    MCP servers

    Hosted memory for AI agents: save what your agent learns and recall it in the next session.

    Stale Official MCP Registry, io.github.fellanH Updated 4 days ago 1 note

  23. Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.

    Stale GitHub, shamspias 406 ★Updated 5 months ago

    git clone https://github.com/shamspias/customizable-gpt-chatbot.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.