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
-
image text to text model by iapp
Source for OpenThai2.1-OCR-Markdown-20261118 (opens huggingface.co) iapp/OpenThai2.1-OCR-Markdown-20261118 -
Clover-35B-A3B-Preview-GGUF
Modelstext generation model by Diffuspace · llama.cpp
Source for Clover-35B-A3B-Preview-GGUF (opens huggingface.co) Diffuspace/Clover-35B-A3B-Preview-GGUF -
ai-coding-deals
Tools & appsMoney-saving guide to AI coding tools: free tiers, discounts, referral credits & open-source alternatives. 省钱指南。
Source for ai-coding-deals (opens github.com) git clone https://github.com/codertesla/ai-coding-deals.git -
show-me-the-story
AI repositories<10 MB — self-hosted AI novel writer in a single Go binary with a web UI. Turn ideas into outlines and chapters with review, foreshadowing, fact-checking, and full-book polish. OpenAI-compatible APIs; Chinese & English.
Source for show-me-the-story (opens github.com) git clone https://github.com/Nigh/show-me-the-story.git -
Overture
MCP serversOverture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.
Source for Overture (opens github.com) git clone https://github.com/SixHq/Overture.git -
copilot
AI repositoriesSource for copilot (opens github.com) git clone https://github.com/opencx-labs/copilot.git -
awesome-generative-ai-data-scientist
AI repositoriesA curated list of 100+ resources for building and deploying generative AI specifically focusing on helping you become a Generative AI Data Scientist with LLMs
Source for awesome-generative-ai-data-scientist (opens github.com) git clone https://github.com/business-science/awesome-generative-ai-data-scientist.git -
Lampline
AI repositoriesBuild AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
Source for Lampline (opens github.com) git clone https://github.com/C4rohan/Lampline.git -
x402-deploy
MCP serversTurn any API or MCP server into a paid service with x402
Source for x402-deploy (opens github.com) git clone https://github.com/nirholas/x402-deploy.git -
Omni-SafetyBench
Datasets & benchmarks[ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
Source for Omni-SafetyBench (opens github.com) git clone https://github.com/THU-BPM/Omni-SafetyBench.git -
kwant
Agents & frameworksYour own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-hosted alternative to Grok Bot, Claude Duet and OpenAI dots. Rust + React.
Source for kwant (opens github.com) git clone https://github.com/alexsergivan/kwant.git -
reevo
Agents & frameworks[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Source for reevo (opens github.com) git clone https://github.com/ai4co/reevo.git -
runtm
Agents & frameworksOpen-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
Source for runtm (opens github.com) git clone https://github.com/runtm-ai/runtm.git -
Raon-1-mini-preview-mlx
Modelstext generation model by KRAFTON · mlx
Source for Raon-1-mini-preview-mlx (opens huggingface.co) KRAFTON/Raon-1-mini-preview-mlx -
claude-brain
SkillsGive Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
Source for claude-brain (opens github.com) git clone https://github.com/memvid/claude-brain.git -
surya-ocr-2.5
Modelsimage text to text model by datalab-to · transformers
Source for surya-ocr-2.5 (opens huggingface.co) datalab-to/surya-ocr-2.5 -
dream-xi-ai
MCP servers🏄 Dream XI AI turns isolated AI agents into a World Cup-level dream team.🏄 Dream XI AI 是一个面向复杂任务执行的 Multi-Agent 协作平台,借鉴足球“梦之队”阵型理念,将不同能力的 AI Agent 抽象为队长、组织核心、前锋、后卫、门将等角色,实现任务规划、工具执行、结果评审、风险拦截和最终交付的协同闭环。
Source for dream-xi-ai (opens github.com) git clone https://github.com/loulanyue/dream-xi-ai.git -
SenseNova-Loop-9B-GGUF
Modelsimage text to text model by sensenova · transformers
Source for SenseNova-Loop-9B-GGUF (opens huggingface.co) sensenova/SenseNova-Loop-9B-GGUF -
Wazuh-MCP-Server
MCP serversWazuh MCP Server: AI-Driven SOC Automation
Source for Wazuh-MCP-Server (opens github.com) git clone https://github.com/INFOKOM-KI/Wazuh-MCP-Server.git -
ChatArena
Agents & frameworksChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Source for ChatArena (opens github.com) git clone https://github.com/Farama-Foundation/ChatArena.git -
image text to text model by turboderp
Source for DeepSeek-V4.1-Flash-1017-exl3 (opens huggingface.co) turboderp/DeepSeek-V4.1-Flash-1017-exl3 -
AI-paper-reviewer
PromptsAI Paper Reviewer: LLM-based tool for academic paper review
Source for AI-paper-reviewer (opens github.com) git clone https://github.com/FanBroWell/AI-paper-reviewer.git -
Marin-Mochi-535B-A23B
Modelstext generation model by open-athena
Source for Marin-Mochi-535B-A23B (opens huggingface.co) open-athena/Marin-Mochi-535B-A23B -
meta-agents-research-environments
Datasets & benchmarksMeta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
Source for meta-agents-research-environments (opens github.com) git clone https://github.com/facebookresearch/meta-agents-research-environments.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.