Self-Hosted AI tools: compare listings

All Self-Hosted tools (43)

agentmemoryPersistent, searchable memory for AI coding agents with 95.2% recall on LongMemEval, running locally on SQLite with MCP, hooks, and 54 tools for Claude Code,.
CumoraCross-platform team chat where AI agents are first-class teammates. Cloud pods or BYOA Claude Code/Codex. Invite-only preview is free.
Hermes AgentSelf-improving open-source AI agent by Nous Research with a built-in learning loop, multi-channel gateway, and model-agnostic runtime. MIT licensed.
LettaMemGPT's company and OSS agent memory runtime. GitHub letta-ai/letta is ~20.5k stars. Cloud is $20 and $200 per project plus usage.
MulticaOpen-source workspace that assigns issues to coding agents as teammates. Self-hostable, 26 CLIs, daemon runs on your machine.
OpenSquillaToken-efficient microkernel AI agent with ML-based smart routing, persistent memory, a layered sandbox, built-in search, and local embeddings. Apache 2.0.
SteelOpen-source browser API for agents. Cloud Launch is $0 plus usage with a one-time $30 credit. Scale is $250/month plus usage.
Vibe SquadMulti-model coding harness: one coordinator routes 71 Markdown specialists across Codex, Claude, Gemini, Grok, and Kimi in git worktrees.
MetaMask Agent WalletA self-custodial wallet for AI agents with immutable spending policies, transaction protection, gas abstraction, and support for autonomous onchain activity.
9RouterFree MIT AI router and token saver that connects Claude Code, Codex, Cursor, and Cline to 40+ providers with auto-fallback and RTK token compression.
ExLlamaV3An efficient local LLM inference library built around the EXL3 quantization format, running large open models on consumer GPUs with tensor and expert parallelism, and powering the TabbyAPI server.
Free Claude CodeMIT local gateway that points Claude Code, Codex, Pi, OpenCode, or Cline at 48 providers.
GMI CloudAI-native GPU cloud. No invented seat.
InsForgeOpen-source agent-native backend: Postgres, auth, storage, edge functions, compute, hosting, and a model gateway driven by CLI and MCP.
MCP India StackMCP India Stack is a MIT offline-first MCP server with 76 Indian tax, identity, and legal tools for agents.
mlx-servemlx-serve is a MIT Zig inference server for Apple Silicon that runs MLX and GGUF locally with OpenAI and Anthropic APIs, no Python.
NInferNInfer is an Apache-2.0 C++/CUDA engine for selected Qwen checkpoints on a single RTX 5090, with OpenAI- and Anthropic-compatible local APIs.
OllamaLocal models plus Ollama cloud. Not a 30-minute Llama3 tutorial.
OmniRouteFree MIT AI gateway with one endpoint, 339 providers, 90+ free tiers, quota-aware fallback, and token compression for Claude Code, Codex, and Cursor.
MySQLOracle relational DB. Not a leftover social-media origin story.
PostgreSQLOpen relational DB. Not a leftover BSD slogan page.
PGVectorPostgres vector extension. Not a Faiss wrapper. No hosted dollar seat.
ValdCloud-native ANN engine.
VespaOSS search+vector engine. Cloud has a free trial; unit table exists. Not an unpriced toolkit.
AnteAntigma Rust harness. Public repo Apache-2.0; binary free in preview. CLI $0 plus BYOK or local GGUF. Not a $20 seat.
ContinueOpen-source coding agent for VS Code and JetBrains. Apache-2.0, local models, CLI, and MCP. Acquired by Cursor; the repo stays public.
MoltbotOpen-source self-hosted AI personal assistant for managing email, calendar, tasks, and workflows. Privacy-focused, cross-platform support. Created by Peter S.
NVIDIA Nsight AINVIDIA CUDA MCP server and Nsight Copilot for coding agents. Hosted docs MCP plus an Apache 2.0 self-hosted blueprint.
OpenClawSelf-hosted AI gateway that sits in WhatsApp, Telegram, Discord, Slack, and more. MIT, ~176k GitHub stars, npm `openclaw`.
PaseoSelf-hosted control plane for Claude Code, Codex, Copilot, OpenCode, and Pi. Desktop, mobile, and web clients. Apache 2.0.
TabbySelf-hosted coding assistant. Apache-2.0 core, not a free cloud Copilot.
KhojSelf-hostable AI second brain: chat with your docs and the web, custom agents, and automations. AGPL-3.0 open source.
MeetilyPrivacy-first AI meeting assistant that transcribes, diarizes, and summarizes calls locally on your device with Ollama, no cloud upload.
OpenSEOOpenSEO is an open-source Semrush and Ahrefs alternative with MCP for agents, usage-based pricing from $10 a month.
DFlash 2Inco AI's Apache 2.0 block-diffusion drafter for speculative decoding. Released 2026-08-18 for Qwen3.8-27B and Muse Glimmer.
IBM Granite 4.2 30BOpen-weight dense reasoning LLM from IBM: 30B parameters, Apache 2.0, native 128K context extendable to 512K, built-in chain-of-thought and reasoning-augmented tool calling.
Ling-3.0-flashinclusionAI MIT hybrid-linear MoE: 124B total, 5.1B active.
Ling-3.0-tinyLing-3.0-tiny is inclusionAI's MIT hybrid-linear MoE: 7.9B total, 1.3B active, for local agents.
MiniCPM5-2BOpenBMB MiniCPM5-2B is a dense 2B on-device LLM with 131k context, Apache-2.0 weights, and cookbooks for vLLM, SGLang, and llama.cpp.
Muse GlimmerMeta's open-weight 30B agentic multimodal model distilled from Muse Spark, designed to run always-on coding and tool-use agents locally on a single consumer.
Qwen3.8-27BAlibaba's open-weight 27B dense companion to Qwen3.8-Max: Apache 2.0 license, multimodal image-text input, built for local deployment and small-batch inference.
Tiel-Coder 35B A3BAgentic coding MoE. Not a lab release.
MiniCPM5 SkillsMiniCPM5 Skills is OpenBMB's SKILL.md pack that routes MiniCPM5 deploy and finetune work across vLLM, SGLang, Ollama, and LoRA tools.

All Tags

A2A Protocol Agent Framework Agent Orchestration Agent Runtime Agent Wallet AI Agent AI Assistant AI Content AI Payments AI Search Alibaba Anthropic API Automation AWS BAAI Black Forest Labs Browser Automation ByteDance Chatbot Claude Claude Code CLI Cloud Cloudflare Code Assistant Code Quality Code Review Codex Coding Agent Cohere Communication Computer Use Crypto & Web3 Cursor Data Science Data Visualization Database Debugging Deep Research Deepgram DeepSeek Deployment Design Developer Tools Document Processing Documentation Education ElevenLabs Embedding Enterprise Evaluation Fine-Tuning FLUX Frontier Model Gemini Gemma Git Go Google GPT GPU Grok Health Hugging Face IBM Image Generation Integration Jina AI Kimi Knowledge Base LangChain LangGraph Linux Llama Local AI Long Context macOS Markdown MCP Meta Microsoft MiniMax Mistral Mixedbread AI Mixture of Experts Model Routing Moonshot AI Multi-Agent Multilingual Multimodal No-Code / Low-Code Nous Research NVIDIA Observability Obsidian Open Source Open Weights OpenAI OpenClaw OpenCode OpenHands OpenRouter Perplexity Presentations Privacy Productivity Project Management Protocol Python Qwen RAG Real-Time Reasoning Replit Reranking Research Rust Sandbox Security Self-Hosted

Items tagged with Self-Hosted (43)

Meetily

Productivity

Privacy-first AI meeting assistant that transcribes, diarizes, and summarizes calls locally on your device with Ollama, no cloud upload.

#Open Source

1000DR: 80AS: 80

MetaMask Agent Wallet

Agent Payment

A self-custodial wallet for AI agents with immutable spending policies, transaction protection, gas abstraction, and support for autonomous onchain activity.

#Self-Hosted

50000000DR: 93AS: 93

Qwen3.8-27B

Models

Alibaba's open-weight 27B dense companion to Qwen3.8-Max: Apache 2.0 license, multimodal image-text input, built for local deployment and small-batch inference.

#Alibaba

20000000DR: 90AS: 95

OpenClaw

Development Tools

Self-hosted AI gateway that sits in WhatsApp, Telegram, Discord, Slack, and more. MIT, ~176k GitHub stars, npm `openclaw`.

#OpenClaw

3000000DR: 70AS: 65

Muse Glimmer

Models

Meta's open-weight 30B agentic multimodal model distilled from Muse Spark, designed to run always-on coding and tool-use agents locally on a single consumer.

#Meta

1000000DR: 95AS: 95

Letta

Agent Infra

MemGPT's company and OSS agent memory runtime. GitHub letta-ai/letta is ~20.5k stars. Cloud is $20 and $200 per project plus usage.

#Self-Hosted

1000000DR: 88AS: 88

Steel

Agent Infra

Open-source browser API for agents. Cloud Launch is $0 plus usage with a one-time $30 credit. Scale is $250/month plus usage.

#Open Source

500000DR: 82AS: 80

Continue

Development Tools

Open-source coding agent for VS Code and JetBrains. Apache-2.0, local models, CLI, and MCP. Acquired by Cursor; the repo stays public.

#Open Source

500000DR: 70AS: 68

Tabby

Development Tools

Self-hosted coding assistant. Apache-2.0 core, not a free cloud Copilot.

#Open Source

150000DR: 55AS: 50

Moltbot

Development Tools

Open-source self-hosted AI personal assistant for managing email, calendar, tasks, and workflows. Privacy-focused, cross-platform support. Created by Peter S.

#Open Source

50000DR: 65AS: 58

Ollama

AI Ecosystem

Local models plus Ollama cloud. Not a 30-minute Llama3 tutorial.

#Llama

1500DR: 165AS: 160

PGVector

Data Models

Postgres vector extension. Not a Faiss wrapper. No hosted dollar seat.

#Vector Database

6893DR: 84AS: 91

Vald

Data Models

Cloud-native ANN engine.

#Vector Database

3730DR: 86AS: 91

Vespa

Data Models

OSS search+vector engine. Cloud has a free trial; unit table exists. Not an unpriced toolkit.

#Vector Database

4120DR: 82AS: 89

PostgreSQL

Data Models

Open relational DB. Not a leftover BSD slogan page.

#Open Source

2670DR: 93AS: 95

MySQL

Data Models

Oracle relational DB. Not a leftover social-media origin story.

#Database

1580DR: 89AS: 90

agentmemory

Agent Infra

Persistent, searchable memory for AI coding agents with 95.2% recall on LongMemEval, running locally on SQLite with MCP, hooks, and 54 tools for Claude Code,.

#Open Source

1000DR: 80AS: 80

Cumora

Agent Infra

Cross-platform team chat where AI agents are first-class teammates. Cloud pods or BYOA Claude Code/Codex. Invite-only preview is free.

#Open Source

1000DR: 80AS: 80

Hermes Agent

Agent Infra

Self-improving open-source AI agent by Nous Research with a built-in learning loop, multi-channel gateway, and model-agnostic runtime. MIT licensed.

#Open Source

1000DR: 80AS: 80

Multica

Agent Infra

Open-source workspace that assigns issues to coding agents as teammates. Self-hostable, 26 CLIs, daemon runs on your machine.

#AI Agent

1000DR: 80AS: 80

OpenSquilla

Agent Infra

Token-efficient microkernel AI agent with ML-based smart routing, persistent memory, a layered sandbox, built-in search, and local embeddings. Apache 2.0.

#AI Agent

1000DR: 80AS: 80

Vibe Squad

Agent Infra

Multi-model coding harness: one coordinator routes 71 Markdown specialists across Codex, Claude, Gemini, Grok, and Kimi in git worktrees.

#Open Source

1000DR: 80AS: 80

9Router

AI Ecosystem

Free MIT AI router and token saver that connects Claude Code, Codex, Cursor, and Cline to 40+ providers with auto-fallback and RTK token compression.

#Open Source

1000DR: 80AS: 80

ExLlamaV3

AI Ecosystem

An efficient local LLM inference library built around the EXL3 quantization format, running large open models on consumer GPUs with tensor and expert parallelism, and powering the TabbyAPI server.

#Local AI

1000DR: 80AS: 80