Results for "self-hosted"

Open-source LLMOps platform combining prompt playground, prompt management, LLM evaluation, and observability.

Open-source AI workspace for building, deploying, and orchestrating AI agents. Visual canvas with 1000+ integrations, multi-framework support (Agno, OpenAI, LangChain, Google ADK), and self-hosted or cloud deployment. Apache 2.0 licensed.

Self-hosted AI workspace combining agents, skills, and tools (Gmail, Calendar, file conversion) that runs entirely on your own provider API keys, sealed in the browser so the server stores none of them. Apache-2.0 licensed.

Open source, local, and self-hosted Amazon Echo/Google Home competitive voice assistant alternative with hardware support. Apache-2.0 licensed.

Self-hosted platform for running a team of persistent AI bots that use tools and MCP servers, keep long-term memory, hand work to each other in shared threads, and can pause to ask a human for approval. MIT licensed.

Open-source Jira, Linear, Monday, and ClickUp alternative. AI-powered project management platform with intelligent task triage, sprint planning, and automated workflows. AGPL-3.0 licensed.

MIT-licensed project workspace coordinating people and AI agents through shared tasks, manager delegation, persistent sandboxes, and human review of delivered work.

Self-hosted platform for running AI employees for small businesses, each with its own mailbox, job description, governed procedures, memory, and place on an org chart, with observable desktop, browser, and terminal sessions. AGPL-3.0 licensed.

MIT-licensed Docker Compose stack for private AI with Ollama, a LiteLLM gateway, chat/RAG, voice, and MCP tooling.

Self-hosted multi-user, multi-agent AI assistant platform featuring long-term memory, MCP tool integration, and sandboxed execution. MIT licensed.

Open-source AI engine running LLMs, vision, voice, image, and video models on any hardware. Self-hosted OpenAI-compatible API. MIT licensed.

Self-hosted ML experiment tracker designed to handle 10,000s of training runs with performant UI and SDK for programmatic access. Apache 2.0 licensed.

Self-hosted webUI for 30+ generative AI models. Generate multimedia content with AI on your own computer, even without dedicated GPU (8GB RAM minimum). Works offline once deployed. GPL-3.0 licensed.

Feature-packed multi-LLM interface.

Apache-2.0-licensed self-hosted local AI stack for inference, chat, voice, agents, workflows, and RAG.

Most popular self-hosted ChatGPT-style interface.

AI observability & evaluation platform.

Self-hosted multi-tenant agent harness combining retrieval, knowledge graph grounding, and workflow orchestration for production teams.

Self-hosted web console for Claude Code on your laptop and remote dev boxes; a daemon on each machine owns the `claude` processes, so sessions keep running when SSH drops (no tmux), and one browser page (phone too) shows every session and which ones wait for you, with a per-session diff. Also runs Codex, OpenCode, and Goose on the local machine over ACP. MIT licensed.

Lightweight personal AI agent with a built-in WebUI, model routing, MCP, and multi-channel chat integrations. MIT licensed.

Universal memory layer for AI agents. Simple API to create RAG applications over any dataset with support for multiple vector stores, embedding models, and LLM providers. Apache 2.0 licensed.

Low-latency, fully modular voice-agent pipeline integrating voice activity detection, speech-to-text, LLMs, and text-to-speech via an OpenAI Realtime-compatible WebSocket API. Apache 2.0 licensed.

State-of-the-art long-term memory for AI agents by Vectorize. Fully self-hosted, MIT-licensed, with integrations for LangChain, CrewAI, LlamaIndex, Vercel AI SDK, and more.

Self-hosted general-purpose agent with durable identity and memory, specialist subagent coordination, and reviewed changes to its own implementation. MIT licensed.