Tag
56 catalogue entries use this topic; each Project's license policy is labeled separately.
Your own personal AI assistant for messaging, work, and the web
OpenClaw is an MIT-licensed open-source personal AI assistant that runs its own gateway and works from WhatsApp, Telegram, Discord, and other connected channels.
Open-source terminal-native AI agent harness from Nous Research
Hermes Agent is Nous Research's open-source terminal-native agent harness that plans and executes supervised tasks on the user's own machine.
Extensible terminal AI coding agent with model choice and tree-structured sessions
Pi is an extensible terminal AI coding agent with a small core, multi-provider model choice, tree sessions, and a TypeScript extension system.
Open-source app people use to manage AI agents for work
Paperclip is an open-source app for managing teams of AI agents for work, with org charts, goals, budgets, and governance, self-hosted via local install, Docker, or a server.
Open-source memory layer for AI agents and apps
Mem0 is an open-source memory layer that gives AI agents and apps persistent memory across sessions, with self-hosted and managed platform options.
Self-hosted AI workspace for chatting with documents and running agents
AnythingLLM is a self-hostable AI workspace for chatting with documents, running AI agents, and switching between local and hosted language models.
The open-source, self-hosted AI chat platform for every model.
LibreChat is a free, self-hosted chat workspace for many AI providers and local models, with agents, retrieval, and team controls.
Open-source Python framework and runtime for building AI agent platforms
Agno is a Python framework and runtime for building agent platforms with memory, knowledge, and tool integrations.
Headless browser built from scratch for AI agents and automation
Lightpanda is an AGPL-3.0-only headless browser written from scratch in Zig for AI agents and automation, driven via CDP and a JavaScript API.
Self-hosted team workspace where humans and AI agents share rooms
Buzz is a self-hosted team workspace where people and AI agents share the same channels, built by Block on a Nostr relay event log.
Open-source AI search and chat across company knowledge
Onyx is a self-hosted AI platform that connects to 50+ work apps to provide permission-aware search and chat across company knowledge.
Open-source low-code platform for internal tools and automations
Budibase is an open-source low-code platform for building internal tools, AI agents, and workflow automations on your own data.
Open-source platform for stateful AI agents with memory
Letta is an open-source platform for building stateful AI agents with persistent memory, background jobs, and multi-agent orchestration.
Open-source AI automation platform with agents, flows, and 760+ app integrations
ActivePieces is an open-source automation platform where teams build AI agents and workflow automations across 760+ connected apps.
Open-source desktop workspace for teams to run AI agents
OpenWork is a free MIT-licensed desktop app that lets teams run AI agents across 50+ models, share skills and MCP servers, and automate browser tasks with their own keys.
Open-source durable execution platform for reliable workflows
Temporal is an open-source durable execution platform that runs code to completion through failures, self-hosted with Docker or Kubernetes or on managed Temporal Cloud.
Open-source AI agents that complete workflows in a real browser
Skyvern is a self-hosted AI platform that completes browser workflows with vision models, with a Playwright-compatible SDK and a managed cloud option.
Open-source RAG assistant that turns docs into chatbots
MaxKB by FIT2CLOUD is an open-source, out-of-the-box RAG assistant that turns documents into a question-answering chatbot with AI workflows and agents. Teams ingest documents and online docs into knowledge bases, connect local or hosted language models, and publish assistants to websites or APIs from a Docker self-hosted deployment.
Desktop Markdown knowledge base with Git sync and AI agents
Tolaria is a free, open source desktop app for Markdown knowledge bases, with wikilinks, an integrated Git client, and AI agent support.
Open-source workflow engine and internal-app platform for code-first teams
Windmill is an open-source developer platform for turning scripts into scheduled workflows, webhooks, and internal apps.
Open-source background jobs and durable AI workflows for TypeScript
Trigger.dev is an open-source platform for building durable AI agents and background workflows in TypeScript, with retries, queues, and observability.
Open-source AI cowork desktop with single-agent and multi-agent workforce modes
Eigent is an open-source desktop app where AI agents work beside you on research, writing, coding, and file tasks across macOS, Windows, and Linux.
Open-source platform for building AI chatbots and support agents
Botpress is an open-source platform for building AI chatbots and support agents with a visual builder, code SDK, and managed cloud.
Isolated Linux sandboxes for running AI agent code
E2B is an open-source cloud that gives each AI agent session its own isolated Linux microVM for running generated code, using tools, and working with files.
Incremental data pipelines that keep AI indexes and RAG context fresh
CocoIndex is a Python framework for building incremental data pipelines that keep search indexes and RAG context in sync with changing sources.
Self-hosted CRM where research agents maintain the pipeline
CRM is a self-hosted, open-source CRM where background research agents maintain company, contact, and deal records for sales teams.
Open-source meta-harness unifying AI coding agents
Omnigent is an Apache-2.0-licensed open-source meta-harness that orchestrates Claude Code, Codex, Cursor, Pi, and custom agents from one workspace.
Open-source browser API for AI agents and apps
Steel is an open-source browser API for AI agents and apps, with managed cloud sessions or a self-hosted Docker image.
Open-source orchestrator for agentic workloads and durable Actors
Rivet is a self-hostable orchestration platform that runs agentic workloads as durable Actors with state, realtime, and scheduling built in.
Durable step functions for event-driven apps and AI agents
Inngest is a durable execution platform for event-driven apps: SDK step functions with checkpoints, retries, and waits run on serverless or your own servers.
Open-source platform connecting AI agents to 600+ tools via MCP
ACI.dev is an open-source tool-calling platform that connects AI agents to 600+ applications through direct function calls or a unified MCP server.
Open-source workspace for building and running AI agents
Agenta is an open-source workspace for building and running AI agents through chat, with scheduling, approvals, versioning, and tracing.
Open-source AI agent observability that finds failures and dispatches fixes
Latitude is an open-source, MIT-licensed observability platform for production AI agents, organized around an Observe, Understand, and Refine loop of tracing, failure signals, and guardrails.
AI-native observability from the Pydantic team, joining LLM calls with telemetry
Logfire is Pydantic's AI-native observability platform for debugging AI applications in production, built on OpenTelemetry so one timeline covers agent model calls, tools, services, databases, and hosts.
Open-source security automation platform for teams and AI agents
Tracecat is an open-source security automation platform for teams and AI agents that combines agents, case management, and workflows in one self-hostable system.
Open-source workplace AI search across company tools
PipesHub is a self-hosted, Apache-2.0 workplace AI platform with permission-aware search and cited answers across 50+ connected work systems.
Persistent AI bots that sign into your tools and finish the work
Rakazo is an Apache-2.0 self-hosted platform for persistent AI bots that sign into your tools, work in sandboxed browsers, and pause for approval.
Open-source OpenTelemetry observability for LLM apps and AI agents
OpenLIT is an Apache-2.0 platform tracing and evaluating LLM apps and AI agents over OpenTelemetry, self-hosted with Docker or Kubernetes.
Open source compliance automation for SOC 2 and ISO 27001
Comp AI is an open source compliance platform that automates evidence collection and audit preparation for SOC 2, ISO 27001, GDPR, and HIPAA.
Self-hosted SERP API returning Google, Bing, and Yandex results as JSON
OpenSERP is a self-hosted, MIT-licensed SERP API that returns Google, Bing, Yandex, and other engine results as structured JSON for AI agents and SEO tools.
Open-core AI code-review agent that enforces your rules on every pull request
Kodus is an open-core AI code-review agent whose reviewer, Kody, comments on pull requests across GitHub, GitLab, Bitbucket, Azure DevOps, and Forgejo or Gitea, enforcing plain-language Kody Rules and business context synced from tools such as Jira, Linear, and Notion.
Open-source BYOK GitHub bot running coding agents inside Actions
Pullfrog is an open-source, model-agnostic GitHub bot that runs Claude Code, Codex, and OpenCode agents inside your GitHub Actions to review PRs, triage issues, and fix CI failures.
Open-source AI chatbot builder for multi-channel assistants
Hexabot is an open-source builder for AI chatbots and support agents with a visual flow editor and document-grounded answers.
Slack-native AI operator that runs workflows across your stack
Pearl is Bubble Lab's Slack-native AI assistant that runs workflows across Gmail, Jira, Notion, GitHub, and 25+ connected tools without code.
Open-source AI agents and workflow automation you can self-host
ByteChef is an open-source platform for building workflow automations and multi-step AI agents across the apps and databases a team already uses.
Open-source TypeScript runtime for autonomous AI agents with memory
AgentOS is a TypeScript runtime for building autonomous AI agents with persistent memory, multi-agent orchestration, and runtime tool generation.
Always-on cloud computers for long-running AI agents
OpenComputer is an open-source cloud that gives each AI agent its own persistent Linux computer with shell, filesystem, and tools.
No-code builder for AI agents and agentic workflows
Giselle is an open source builder for AI agents and agentic workflows, pairing a drag-and-drop visual editor with a managed cloud at studio.giselles.ai.
Open-source chat and AI-agent SDKs for web and mobile apps
Ethora is an open-source chat and AI-agent platform with SDKs that add messaging, chatbots, and RAG search to web and mobile apps.
Open-source AI browser with built-in agents for research and automation
Browser Operator is an open-source, Chromium-based AI browser that runs search, research, and workflow agents inside the browser window.
Open-source live chat and AI agents for customer support
Tiledesk is an open-source live-chat and AI chatbot platform with a no-code design studio, knowledge-base RAG, and human-agent handoff.
Self-hosted cloud coding agent that turns chat messages into reviewed PRs
Roomote is a self-hostable cloud coding agent from the Roo Code team. Assign it work from chat and it codes in an isolated sandbox, then opens a pull request with screenshots and a preview link.
CLI-first bank account for AI agents with human-approved transfers
0 Finance is a CLI-first financial workflow project for agent-driven invoicing, transfer proposals, and human approvals. Its current site says the product is being deprecated and new signups are disabled. Agents and scripts use the zero command line tool to check balances, create and send invoices, propose ACH or IBAN transfers, and view savings positions. Read operations run immediately, while transfers and withdrawals become proposals that a person reviews in the companion web dashboard. The same primitives are reachable through an HTTP API and an MCP server for assistants. Accounts hold funds as USDC in self-custody wallets, with idle balances allocated to lending protocols for variable yield and smart-contract failures insured up to a stated limit. The hosted dashboard serves existing customers, and the MIT-licensed codebase can be forked and run independently with Docker. The vendor states the product is being deprecated and has disabled new signups. No public pricing is documented. A full independent deployment also needs credentials for third-party auth and payment providers, so self-hosting is nontrivial.
Privacy-first web analytics for humans and AI agents, self-hosted or in EU/US cloud
HitKeep is a privacy-first web analytics platform that tracks humans and AI agents without cookies, fingerprinting, or cross-site identifiers. Sites add one lightweight script under their own domain, and an MCP server plus analytics API expose the same stats to agents and external tools.
Email inbox API that gives every AI agent its own address
AgentMail is an API-first email service that gives AI agents their own inboxes to send, receive, and track messages programmatically.
The agentic development environment
Warp is a proprietary, terminal-based agentic development environment from Warp that combines a command-line terminal, an AI agent mode, and built-in code editing and review workflows in one desktop application.