Library
87,622 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
soul.md
Agents & frameworksA portable, provider-agnostic specification for AI agent personas
Source for soul.md (opens github.com) git clone https://github.com/rokoss21/soul.md.git -
UltraData-Code
Datasets & benchmarksHugging Face dataset by openbmb
Source for UltraData-Code (opens huggingface.co) openbmb/UltraData-Code -
Awesome-GUI-Agent-Security
Agents & frameworksGUI / Computer-Use / Browser Agent 安全论文清单 —— 按攻防轴组织,每篇附中文简介
Source for Awesome-GUI-Agent-Security (opens github.com) git clone https://github.com/Yuxuan2003/Awesome-GUI-Agent-Security.git -
llm
AI repositories[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models
Source for llm (opens github.com) git clone https://github.com/rustformers/llm.git -
harnessrouter
Agents & frameworksHarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Source for harnessrouter (opens github.com) git clone https://github.com/HarnessRouter/harnessrouter.git -
recall-loom
SkillsProject memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.
Source for recall-loom (opens github.com) git clone https://github.com/Frappucc1no/recall-loom.git -
lumi-4b
Modelstext generation model by ceia-research
Source for lumi-4b (opens huggingface.co) ceia-research/lumi-4b -
text generation model by FrostWolfAI · gguf
Source for Spark-X2.6-4B-abliterated-GGUF (opens huggingface.co) FrostWolfAI/Spark-X2.6-4B-abliterated-GGUF -
Textus
AI repositoriesThe next-generation Markdown editor, with an AI writing assistant. Free and open source for macOS, Windows and Linux.
Source for Textus (opens github.com) git clone https://github.com/CatVinci-Studio/Textus.git -
localharness
Agents & frameworksAn open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).
Source for localharness (opens github.com) git clone https://github.com/ahwurm/localharness.git -
videodb-python
AI repositoriesVideoDB Python SDK
Source for videodb-python (opens github.com) git clone https://github.com/video-db/videodb-python.git -
Spark-X2.6-1.7B
Modelstext generation model by XHToken · transformers
Source for Spark-X2.6-1.7B (opens huggingface.co) XHToken/Spark-X2.6-1.7B -
geobench
Datasets & benchmarksGeoGuessr benchmark for language models
Source for geobench (opens github.com) git clone https://github.com/ccmdi/geobench.git -
ai-agent-skills
PromptsAI agent skills for production grade applications
Source for ai-agent-skills (opens github.com) git clone https://github.com/DevelopersGlobal/ai-agent-skills.git -
pydantic-deepagents
Agents & frameworksOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Source for pydantic-deepagents (opens github.com) git clone https://github.com/vstorm-co/pydantic-deepagents.git -
Ultra-FineWeb-L1
Datasets & benchmarksHugging Face dataset by openbmb
Source for Ultra-FineWeb-L1 (opens huggingface.co) openbmb/Ultra-FineWeb-L1 -
ste80-humanizer
SkillsSTE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.
Source for ste80-humanizer (opens github.com) git clone https://github.com/Dodaios/ste80-humanizer.git -
gamebot
Datasets & benchmarks[ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
Source for gamebot (opens github.com) git clone https://github.com/Visual-AI/gamebot.git -
ai--manus2.0
Agents & frameworksAI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
Source for ai--manus2.0 (opens github.com) git clone https://github.com/tornadonovicewhirl40/ai--manus2.0.git -
ai--manus2.0
Agents & frameworksAI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
Source for ai--manus2.0 (opens github.com) git clone https://github.com/TitanShieldRavine/ai--manus2.0.git -
cap-evolve
PromptsOptimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
Source for cap-evolve (opens github.com) git clone https://github.com/skillberry-ai/cap-evolve.git -
S5-nano
Modelsimage text to text model by maritaca-ai · transformers
Source for S5-nano (opens huggingface.co) maritaca-ai/S5-nano -
taracode
Agents & frameworksDevOps & Cloud SI Assistant that runs locally on taraengine for complete privacy.
Source for taracode (opens github.com) git clone https://github.com/tara-vision/taracode.git -
GLiDE
Modelsimage text to text model by fastino · transformers
Source for GLiDE (opens huggingface.co) fastino/GLiDE
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.