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
-
TerminalWorld
Datasets & benchmarksTerminalWorld: Benchmarking Agents on Real-World Terminal Tasks (NeurIPS 2026 Evaluations and Datasets Track)
Source for TerminalWorld (opens github.com) git clone https://github.com/terminalworld/TerminalWorld.git -
UHGEval
Datasets & benchmarks[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.
Source for UHGEval (opens github.com) git clone https://github.com/IAAR-Shanghai/UHGEval.git -
text generation model by huihui-ai · transformers
Source for Huihui-GLM-5.3-abliterated-GGUF (opens huggingface.co) huihui-ai/Huihui-GLM-5.3-abliterated-GGUF -
PharosRAG
MCP serversPharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
Source for PharosRAG (opens github.com) git clone https://github.com/Laurent00TT/PharosRAG.git -
flowflow
AI repositoriesAgentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite
Source for flowflow (opens github.com) git clone https://github.com/mirkobozzetto/flowflow.git -
text generation model by bartowski
Source for Nanbeige_Nanbeige4.3-33B-GGUF (opens huggingface.co) bartowski/Nanbeige_Nanbeige4.3-33B-GGUF -
teros
Agents & frameworksThe source-available AI agent operating system
Source for teros (opens github.com) git clone https://github.com/teros-hq/teros.git -
awesome-claude-skills
Skills🎯 The definitive collection of 50+ verified Awesome Claude Skills for Claude Code, Claude.ai, and API. Boost productivity with TDD, debugging, git workflows, document processing, and more. Community-driven, actively maintained.
Source for awesome-claude-skills (opens github.com) git clone https://github.com/karanb192/awesome-claude-skills.git -
image text to text model by drowzeys · transformers
Source for keys-DeepSeek-V4.1-Flash-1017-Abliterated (opens huggingface.co) drowzeys/keys-DeepSeek-V4.1-Flash-1017-Abliterated -
Corum-Harness
Agents & frameworks基于 Deepseek-Harness 核心底座打造的桌面版 Agent.继承底坐全部能力。并补全 IDE 相关功能。
Source for Corum-Harness (opens github.com) git clone https://github.com/kukucaiCndy/Corum-Harness.git -
KESTREL
PromptsJailbreak system prompt. One file, one speaker, no second-guessing. Paste it as the system prompt on any provider.
Source for KESTREL (opens github.com) git clone https://github.com/Irsyadmr354/KESTREL.git -
llmslim
MCP serversLong-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
Source for llmslim (opens github.com) git clone https://github.com/Thanatos9404/llmslim.git -
Tess-4.5-27B
Modelsimage text to text model by migtissera · transformers
Source for Tess-4.5-27B (opens huggingface.co) migtissera/Tess-4.5-27B -
agentic-loop-engineering-course
Docs & tutorialsAn 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.
Source for agentic-loop-engineering-course (opens github.com) git clone https://github.com/FareedKhan-dev/agentic-loop-engineering-course.git -
knowns
Agents & frameworksTasks, docs, specs and decisions for AI coding agents, as markdown in your repo. Keeps the agent from breaking architectural decisions you already made.
Source for knowns (opens github.com) git clone https://github.com/knowns-dev/knowns.git -
life-distributable
Agents & frameworksA personal agent that works on your life around the clock, on a Mac you own. One sentence to Claude Code installs it.
Source for life-distributable (opens github.com) git clone https://github.com/mattabate/life-distributable.git -
Long-Horizon-Terminal-Bench
Datasets & benchmarksHugging Face dataset by IntelligenceLab
Source for Long-Horizon-Terminal-Bench (opens huggingface.co) IntelligenceLab/Long-Horizon-Terminal-Bench -
quackd
Agents & frameworksThe communication layer between people and robots, and between robots. Talk to any robot in your own words, with an LLM for its brain. Robots that have never met check each other's passports and share the work. Microduck, Huebot, Open Duck Mini, LeRobot arms, XLeRobot carts, AlohaMini, ToddlerBot, MOSS, ROS bases and industrial arms on ROS 2.
Source for quackd (opens github.com) git clone https://github.com/rokbenko/quackd.git -
Awesome-Graphs-Meet-Agents
Agents & frameworks[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents & Agentic Graph Engineering).
Source for Awesome-Graphs-Meet-Agents (opens github.com) git clone https://github.com/YuanchenBei/Awesome-Graphs-Meet-Agents.git -
Cairn
AI repositoriesOpen-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with relational structure.
Source for Cairn (opens github.com) git clone https://github.com/xcosmosbox/Cairn.git -
TIA_Portal_Openness_MCP
MCP serversDrive Siemens TIA Portal V20/V21 (STEP 7, WinCC Unified) from any MCP client — create projects, generate PLC & HMI, compile & diagnose. Prebuilt runtime, no Openness coding required.
Source for TIA_Portal_Openness_MCP (opens github.com) git clone https://github.com/bulaofen0036-coder/TIA_Portal_Openness_MCP.git -
scope-recall-hermes
Agents & frameworksLocal long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered.
Source for scope-recall-hermes (opens github.com) git clone https://github.com/410979729/scope-recall-hermes.git -
LFM3-VL-2B-GGUF
Modelsimage text to text model by LiquidAI · gguf
Source for LFM3-VL-2B-GGUF (opens huggingface.co) LiquidAI/LFM3-VL-2B-GGUF -
raft
AI repositoriesRAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.
Source for raft (opens github.com) git clone https://github.com/lumpenspace/raft.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.