Library
86,689 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
-
lumi-4b
Modelstext generation model by ceia-research
ceia-research/lumi-4b -
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.
git clone https://github.com/HarnessRouter/harnessrouter.git -
text generation model by FrostWolfAI · gguf
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.
git clone https://github.com/CatVinci-Studio/Textus.git -
Spark-X2.6-1.7B
Modelstext generation model by XHToken · transformers
XHToken/Spark-X2.6-1.7B -
deltallm
MCP serversSelf-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.
git clone https://github.com/deltawi/deltallm.git -
geobench
Datasets & benchmarksGeoGuessr benchmark for language models
git clone https://github.com/ccmdi/geobench.git -
ai-agent-skills
PromptsAI agent skills for production grade applications
git clone https://github.com/DevelopersGlobal/ai-agent-skills.git -
image text to text model by huihui-ai · transformers
huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF -
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.
git clone https://github.com/vstorm-co/pydantic-deepagents.git -
gamebot
Datasets & benchmarks[ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
git clone https://github.com/Visual-AI/gamebot.git -
Ultra-FineWeb-L1
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/Ultra-FineWeb-L1 -
cap-evolve
PromptsOptimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
git clone https://github.com/skillberry-ai/cap-evolve.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.
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.
git clone https://github.com/TitanShieldRavine/ai--manus2.0.git -
taracode
Agents & frameworksDevOps & Cloud SI Assistant that runs locally on taraengine for complete privacy.
git clone https://github.com/tara-vision/taracode.git -
S5-nano
Modelsimage text to text model by maritaca-ai · transformers
maritaca-ai/S5-nano -
GLiDE
Modelsimage text to text model by fastino · transformers
fastino/GLiDE -
claude-code-prompts
PromptsIndependently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
git clone https://github.com/repowise-dev/claude-code-prompts.git -
tokin
Agents & frameworksMake any agent harness token-native.
git clone https://github.com/open-rollout/tokin.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.
git clone https://github.com/Torusdrasocket/ai--manus2.0.git -
o11y-bench
Datasets & benchmarksOpen benchmark on observability tasks built on Harbor
git clone https://github.com/grafana/o11y-bench.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.
git clone https://github.com/TremorRatTackle/ai--manus2.0.git -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.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.