InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

9,976 results Clear search and filters
  1. Awesome-Agent-Memory

    AI repositories

    Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

    Indexed GitHub, TeleAI-UAGI 713 ★Apache-2.0Updated yesterday

    git clone https://github.com/TeleAI-UAGI/Awesome-Agent-Memory.git
  2. LightMem

    AI repositories

    [ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

    Stale GitHub, zjunlp 1,211 ★MITUpdated 10 days ago

    git clone https://github.com/zjunlp/LightMem.git
  3. A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

    Stale GitHub, CodeAbra 912 ★MITUpdated 25 days ago

    git clone https://github.com/CodeAbra/iai-personal-memory-engine.git
  4. nautilus-compass

    Datasets & benchmarks

    Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

    Indexed GitHub, chunxiaoxx 1,258 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/chunxiaoxx/nautilus-compass.git
  5. gentle-ai

    Skills

    Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

    Indexed GitHub, Gentleman-Programming 9,236 ★MITUpdated today

    git clone https://github.com/Gentleman-Programming/gentle-ai.git
  6. text generation model by meta-llama · transformers

    Stale Hugging Face Hub, meta-llama 654 ♥llama2Updated 2 years ago 1 note

    meta-llama/Llama-2-13b-hf
  7. GPTCache

    AI repositories

    Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

    Stale GitHub, zilliztech 8,211 ★MITUpdated 55 days ago

    git clone https://github.com/zilliztech/GPTCache.git
  8. Llama-2-70b

    Models

    text generation model by meta-llama

    Stale Hugging Face Hub, meta-llama 536 ♥llama2Updated 2 years ago 1 note

    meta-llama/Llama-2-70b
  9. hertzbeat

    AI repositories

    An AI-powered next-generation open source real-time observability system.

    Stale GitHub, apache 7,463 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/apache/hertzbeat.git
  10. powercontext

    Agents & frameworks

    Not only memory but a full story

    Stale GitHub, oceanbase 1,385 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/oceanbase/powercontext.git
  11. CADAM

    Agents & frameworks

    CADAM is the open source text-to-CAD web application

    Stale GitHub, Adam-CAD 5,266 ★GPL-3.0Updated 40 days ago

    git clone https://github.com/Adam-CAD/CADAM.git
  12. Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.

    Stale GitHub, eugeniughelbur 5,216 ★MITUpdated 8 days ago

    git clone https://github.com/eugeniughelbur/obsidian-second-brain.git
  13. Curated list of Agent Skills centered on people, relationships, commemorative scenes, and methodological perspectives

    Stale GitHub, xixu-me 4,703 ★CC0-1.0Updated 29 days ago

    git clone https://github.com/xixu-me/awesome-persona-distill-skills.git
  14. shepherd

    Tools & apps

    A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

    Stale GitHub, shepherd-agents 2,483 ★MITUpdated 2 months ago

    git clone https://github.com/shepherd-agents/shepherd.git
  15. VGGT-Omega

    Models

    model by facebook

    Indexed Hugging Face Hub, facebook 679 ♥otherUpdated 2 months ago 1 note

    facebook/VGGT-Omega
  16. holaOS

    MCP servers

    Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.

    Indexed GitHub, holaboss-ai 11.4k ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/holaboss-ai/holaOS.git
  17. MegaTTS3

    Models

    text to speech model by ByteDance

    Stale Hugging Face Hub, ByteDance 419 ♥apache-2.0Updated 19 months ago

    ByteDance/MegaTTS3
  18. image text to text model by meta-models · transformers

    Stale Hugging Face Hub, meta-models 745 ♥otherUpdated 32 days ago 1 note

    meta-models/Muse-Spark-Open-816B-A42B
  19. image text to text model by google · transformers

    Stale Hugging Face Hub, google 461 ♥otherUpdated 16 months ago 1 note

    google/medgemma-27b-it
  20. weave

    Agents & frameworks

    Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge.

    Stale GitHub, Ataraxy-Labs 1,348 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/Ataraxy-Labs/weave.git
  21. medical

    Datasets & benchmarks

    Hugging Face dataset by shibing624

    Indexed Hugging Face Hub, shibing624 454 ♥apache-2.0Updated 2 years ago

    shibing624/medical
  22. agentset

    AI repositories

    The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

    Stale GitHub, agentset-ai 2,115 ★MITUpdated 19 days ago

    git clone https://github.com/agentset-ai/agentset.git
  23. fable-method

    Skills

    The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

    Stale GitHub, Sahir619 2,300 ★MITUpdated 44 days ago

    git clone https://github.com/Sahir619/fable-method.git
  24. ClinicalBERT

    Models

    fill mask model by medicalai · transformers

    Stale Hugging Face Hub, medicalai 390 ♥Updated 19 months ago

    medicalai/ClinicalBERT

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.