Library
86,235 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 research potential clients
-
AgenticX
Agents & frameworksAgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
git clone https://github.com/DemonDamon/AgenticX.git -
Clover-35B-A3B-Preview
Modelstext generation model by Diffuspace · transformers
Diffuspace/Clover-35B-A3B-Preview -
EdgeBox
Agents & frameworksA fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other desktop applications just like humans. Based on E2B oss code.
git clone https://github.com/BIGPPWONG/EdgeBox.git -
HiRoute
Agents & frameworksMake Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
git clone https://github.com/higress-group/HiRoute.git -
PS5LM
AI repositoriesllama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
git clone https://github.com/cobanov/PS5LM.git -
apktool-mcp-server
MCP serversA MCP Server for APK Tool (Part of Android Reverse Engineering MCP Suites)
git clone https://github.com/zinja-coder/apktool-mcp-server.git -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
Llama-3.1-70B
Modelstext generation model by meta-llama · transformers
meta-llama/Llama-3.1-70B -
SkyPile-150B
Datasets & benchmarksHugging Face dataset by Skywork
Skywork/SkyPile-150B -
image text to text model by dealignai · transformers
dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 -
RustXNG
AI repositoriesSelf-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.
git clone https://github.com/RustXNG/RustXNG.git -
Hermes-3-Llama-3.1-8B
Modelstext generation model by NousResearch · transformers
NousResearch/Hermes-3-Llama-3.1-8B -
image text to text model by meta-llama · transformers
meta-llama/Llama-4-Maverick-17B-128E-Instruct -
dreamcoder
AI repositoriesA locally run, multi-provider AI coding workspace · 本地运行、支持多家模型服务商的 AI 编程工作台
git clone https://github.com/GoDiao/dreamcoder.git -
Argus
Agents & frameworksOpen-source red-team testing for AI agents. 295 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.
git clone https://github.com/gy15901580825/Argus.git -
any to any model by nvidia · transformers
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 -
superglue
Tools & appssuperglue's AI agents connect, migrate and implement enterprise systems. Cloud-hosted or on your own infrastructure.
git clone https://github.com/superglue-ai/superglue.git -
d1-3B
Modelsimage text to text model by LiquidAI · transformers
LiquidAI/d1-3B -
Qwen3.8-27B-DFlash2
Modelstext generation model by z-lab · transformers
z-lab/Qwen3.8-27B-DFlash2 -
Ornith-1.5-122B
Modelstext generation model by ornith-ai · transformers
ornith-ai/Ornith-1.5-122B -
moai-adk
Agents & frameworksAgentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
git clone https://github.com/modu-ai/moai-adk.git -
awesome-instruction-datasets
PromptsA collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
git clone https://github.com/jianzhnie/awesome-instruction-datasets.git -
Yunjue-Agent
Agents & frameworksYunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
git clone https://github.com/YunjueTech/Yunjue-Agent.git -
obsidian-gemini-helper
Tools & appsAI chat, workflow automation, semantic search (RAG), LLM Wiki (OKF) powered by Google Gemini. Works on both desktop and mobile.
git clone https://github.com/takeshy/obsidian-gemini-helper.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.