AgentSidekick

Local Inference

Running models on your own machine. As of 2026-11-21, 256 indexed products offer it (150 with full profiles), in 10 forms: 188 MCP servers, 16 IDE extensions, 15 Infrastructure, 11 Frameworks. 89 were published in the last 90 days, against 54 in the 90 days before. cherry-studio has the most GitHub stars, 16% of the total across 239 products with their own repository.

CapabilitySegment label: Crowded, slowing DER

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 188 indexed · 84 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Local Inference: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1MaxKB🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。1Panel-dev23ktoday
2docker-androidAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agentbudtmo16k2d ago
3osaurusOwn your AI. The open-source agent harness for macOS. Run local or cloud models with persistent memory, skills, tools, and autonomous execution. Built in Swift.osaurus-ai8.2ktoday
4bla🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).qybaihe6.4ktoday
5deep-researchUse any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.u14app4.7k5mo ago
6pipeshub-aiThe open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.pipeshub-ai4.1ktoday
7chat-ollamaChatOllama is an open source agentic app for running AI agents across local and hosted models.sugarforever3.5k3d ago
8agency-orchestrator🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。jnMetaCode2.5k10d ago
9blender-ai-mcp-addonAI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon, copilot for 3D, bpy Python scripting, MCP integration.bookwjitchieni19861.9k2d ago
10DiveDive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨OpenAgentPlatform1.8k3mo ago

All 84 profiled MCP servers with this capability

IDE extensions 16 indexed · 17 profiled

No compatibility evidence is collected for this form.

Local Inference: IDE extensions by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1twinny - AI Code Completion and ChatAI code completion, chat, inline edit and code review on models you run. Private, open source, one gateway for the whole team.twinnydotdev3.7k3d ago
2llama-vscodeLocal LLM-assisted text completion using llama.cppggml-org1.6k1d ago
3ChatGPT CopilotAn VS Code ChatGPT Copilot Extensionfeiskyer1645mo ago
4Dish AI Commit Message Gen🤖 AI-Powered VSCode extension for generating standardized Git/SVN commit messages. ✨ Supports 20+ AI services: OpenAI, Ollama, VS Code AI, Zhipu AI, DashScope, Doubao AI, Gemini, Deepseek, Anthropic, Mistral, Azure OpenAI, VertexAI, LMStudio and more. 🌍 19 languages supported. 📊 Features: AI commit generation, code review, weekly reports, branch naming, PR summaries, token statistics.littleCareless1631mo ago
5CodeBuddy: Deep Coding Agent — Bring Your Own ModelA LangGraph/deepagents coding agent that lives in VS Code — it plans, reads your codebase, edits (AST-aware), runs commands, searches, and reviews. Bring your own model and keys: Anthropic, Gemini, OpenAI, Groq, DeepSeek, Qwen, GLM, xAI Grok, or a local model. MCP-native, security-first, MIT-licensed.fiatinnovations1422mo ago
6GitHub Copilot API GatewayFree & open-source universal API Gateway for all VS Code language models. Auto-discovers GitHub Copilot, Gemini, Ollama & any AI extension — exposing them via local OpenAI, Anthropic, Google & Llama compatible APIs. One endpoint, every model. Use with Cursor, LangChain, Agents & more.Suhaib Bin Younis1344d ago
7Commit SageFree AI commit messages using Gemini, OpenRouter, Groq, Claude, DeepSeek, xAI, Ollama, or any OpenAI-compatible LLMVizzleTF534d ago
8Bandit StealthFree, local-first coding agent for VS Code — run Ollama models (Gemma, Qwen, Devstral) with tool use, diff approvals, and voice. Optional Bandit cloud.Burtson Labs93d ago
9GitMind: AI Commit Message GeneratorAI commit message generator for VS Code. Write clear Conventional Commits from your diff with GitHub Copilot, local Ollama, or 24 built-in AI providers.ShahabBahreiniJangjoo52d ago
10Lattice AILattice AI extension for the local-first Digital Brain that keeps your knowledge durable across any AI model.parktaesoo21d ago

All 17 profiled IDE extensions with this capability

Infrastructure 15 indexed · 13 profiled

No compatibility evidence is collected for this form.

Local Inference: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1LEANN[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.StarTrail-org14ktoday
2langchain4jLangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.langchain4j13ktoday
3SoupFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.MakazhanAlpamys11ktoday
4cube-studiocube studio开源云原生一站式机器学习/深度学习/大模型AI平台,mlops算法链路全流程,算力租赁平台,notebook在线开发,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务VGPU虚拟化,边缘计算,标注平台自动化标注,deepseek等大模型sft微调/奖励模型/强化学习训练,vllm/ollama/mindie大模型多机推理,私有知识库,AI模型市场,支持国产cpu/gpu/npu 昇腾生态,支持RDMA,支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano等分布式tencentmusic5.1k1mo ago
5cube-studiocubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台,算法全链路流程,多租户,算力租赁平台,token中转,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务,VGPU虚拟化,云边端协同,边缘计算,自动化标注平台,deepseek等大模型sft微调/奖励模型/强化学习训练,vllm/ollama/mindie大模型多机推理,私有知识库llmops智能体,AI模型市场,支持国产异构算力调度,昇腾/寒武纪/海光/摩尔/沐曦等,支持ib/roce/RDMA,信创支持data-infra2.6k1mo ago
6RAGLightRAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.Bessouat406721mo ago
7LynkrStreamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.Fast-Editor6426d ago
8embedJsA NodeJS RAG framework to easily work with LLMs and embeddingsllm-tools6014mo ago
9juliusSimple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in secondspraetorian-inc256today
10heronAgent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.Netis1041mo ago

All 13 profiled Infrastructure with this capability

Frameworks 11 indexed · 10 profiled

No compatibility evidence is collected for this form.

Local Inference: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1open-multi-agentSelf-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.open-multi-agent7.1k4d ago
2koogKoog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problemsJetBrains4.7k11d ago
3ObserverThe micro-agent orchestrator that monitors anything for you. Running completely locally. Open Source.Roy38381.8ktoday
4Agentlas-OSThe Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.agentlas-ai1.4ktoday
5PhoneClawPhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.kellyvv1.3k3mo ago
6samplesAgent samples built using the Strands Agents SDK.strands-agents9433d ago
7pocketpawYour AI agent in 30 seconds. Not 30 hours. Self-hosted, open-source personal AI with desktop installer, multi-agent Command Center(Deep Work), and 7-layer security. Anthropic, OpenAI, or Ollama.pocketpaw9351d ago
8Deuz-SDKTypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.Deuz-AI5081mo ago
9Abu-CoworkOpen-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Local-first, with Claude, OpenAI, DeepSeek and Ollama.PM-Shawn4248d ago
10animaworksOrganization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).xuiltul2685d ago

Agent projects 8 indexed · 8 profiled

No compatibility evidence is collected for this form.

Local Inference: Agent projects by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1CodewhaleAn open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read.codewhale-hq41ktoday
2BrowserOS🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.browseros-ai14ktoday
3aichatAll-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.sigoden11k9mo ago
4big-AGIThe AI workspace for experts. Switch across 800+ models mid-chat, tune 40+ parameters, Beam models side by side. BYO keys, self-hostable. Built on our native-protocol engine: reliable, hyper-configurable, and fast.enricoros7.2ktoday
5LongMemoryLocal persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.CaviraOSS4.6k11d ago
6agentic-rag-for-dummiesA modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.GiovanniPasq4.4k10d ago
7little-coderA harness optimized to smaller LLMsitayinbarr2.7k2mo ago
8zeroThe coding agent that answers to you, your model, your machine, your rules.Twigpine1.8k1d ago

Agent skills 8 indexed · 8 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Local Inference: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1cherry-studioYour AI workspace for models, agents, and productivity.CherryHQ54ktoday
2pinvou-agentOpen-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.Pinvou3.0ktoday
3claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).anthropics—5d ago
4add-ollama-toolAdd Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.nanocoai—today
5add-ollama-providerRoute a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.nanocoai—today
6gguf-quantizationGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.Orchestra-Research—1mo ago
7llama-cppRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.Orchestra-Research—1mo ago
8inference-serving-llama-cppRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.davila7—today

Plugins 5 indexed · 5 profiled

5 of these are Claude plugins, which Claude Code documents (protocol-level). DER

Local Inference: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1claude-octopusRun multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.nyldn4.5k2d ago
2octov11.26.0 - Custom provider presets in the tool helper, native skills and debate advisor checks. 31 personas, 56 commands, 64 skills. Run /octo:setup.nyldn4.5k2d ago
3claude-councilClaude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity, Kimi and any model OpenRouter routes to over API; codex, antigravity, grok, kimi and cursor CLIs on subscription auth; ollama locally. Codex specialists take coding tasks on their own branch (experimental).hex9514d ago
4lumenPrecise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server — no cloud, no npm.ory3171mo ago
5forkmindLocal-first LLM branching & debugging. Treat AI context windows like a Git repo — capture, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, and MCP for agents.ccplugins—3mo ago

Libraries 3 indexed · 3 profiled

No compatibility evidence is collected for this form.

Local Inference: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1a2a-adapterOpen Source A2A Protocol Adapter SDK for Different Agent Frameworks and Harnesseshybroai108today
2ai-mocks🤖 AI-Mocks is a Kotlin-based toolkit for mocking and testing LLM APIs with real streaming and SSE support. Simulate OpenAI, Anthropic, Gemini, Ollama, and A2A services locally for reliable integration testing.mokksy531d ago
3HandlerA2A protocol client for your terminalalDuncanson476d ago

Developer tools 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Local Inference: Developer tools by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1AgentOpsSDK and dashboard for monitoring agent sessions, tool calls, costs and failures, with integrations for CrewAI, OpenAI Agents SDK, AG2 and others.AgentOps6.0k4mo ago

Rules packs 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Local Inference: Rules packs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1vybe-intelligence-vaultAn auto-updating open-source vault for AI agents, RAG systems, MCP servers, prompts, tools, templates, and next-generation web development.rxmna850223today

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
GitHub52.0%
Android41.6%
Blender41.6%
Obsidian41.6%
Azure20.8%
PostgreSQL20.8%
Confluence10.4%
Gmail10.4%
Jira10.4%
Microsoft Excel10.4%
OpenAPI10.4%
Slack10.4%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
ollama220
llama.cpp2
lm studio9
local inference0
run models locally0
gguf17
mlx8

Segment statistics

Whole catalogue (256 indexed products). Calculated 2026-11-21.

256DERIndexed products150 with full profiles
89DERLaunched, last 90 days54 in the 90 days before
21DERMomentum vs catalogue50 = same pace as the catalogue
16%DERLargest project's share of starsAcross 239 products with their own repository
0.060DERConcentration (HHI)About 17 equal-sized projects’ worth; unconcentrated
17SRCMedian starsPer product with its own repository
88%DEROpen sourceMarked open source; unknown counts as not

Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.060 means stars are spread as if across about 17 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .