Run local language models through a chat interface or compatible API.
Project overview
TextGen provides portable desktop builds and a web interface for loading local models, including GGUF files, and using them for chat, vision, document questions, and free-form generation. It can switch among several inference backends and expose OpenAI- and Anthropic-compatible endpoints with tool calling and MCP support. Core use can remain fully offline with no telemetry, while training, additional backends, image generation, and some extensions require the full installation.
General agentProductivity and officeModel Context Protocol
aiden
@taracodlabs·TypeScript
Run a local Windows agent that operates browsers, terminals, and workflows.
Project overview
Aiden is a Windows-native, local-first autonomous agent that can operate a browser and terminal, invoke tools, run workflows, and persist memory and job state on the user's machine. It supports multiple model providers, subagents, scheduled or external triggers, and long-running work with verification, retries, recovery, and resume behavior. The project is released under AGPL-3.0.
AutomationTesting and debuggingModel Context Protocol
testzeus-hercules
@test-zeus-ai·Python
Turn Gherkin scenarios into automated end-to-end browser tests.
Project overview
Hercules converts readable Gherkin feature files into automated end-to-end browser tests, using Playwright to interact with web applications and producing JUnit XML and HTML reports. It is useful for QA or business teams that want to describe behavior without writing test code. The agent can consume tools from external MCP servers or run as an MCP server that exposes test generation, execution, and result retrieval.
Desktop appProductivity and officeModel Context Protocol
CodePilot
@op7418·TypeScript
Connect multiple AI providers in a desktop agent with MCP, skills, and mobile bridges.
Project overview
CodePilot is a desktop agent client for coding and general assistant work, with configurable model providers, persistent workspace memory, MCP servers, reusable skills, scheduled tasks, and image generation. Telegram, Feishu, Discord, QQ, and WeChat bridges let you send requests from a phone. Claude Code CLI is optional for chat, but required for direct file editing, terminal commands, and Git operations.
General agentProductivity and officeModel Context Protocol
Abu-Cowork
@PM-Shawn·TypeScript
Plan and execute local desktop tasks across files, commands, browsers, and documents.
Project overview
Abu Cowork is a local-first desktop AI agent that can plan multi-step work, read and write files, run commands, control a real browser, and create documents or web pages from natural-language requests. Risky actions such as deletion, overwriting, sending, or installation can be placed behind a reviewable plan and explicit approval. Each conversation can use its own model and permission mode. The app also supports installable skills, MCP connectors, schedules, and team messaging channels for broader automation.
Web appProductivity and officeModel Context Protocol
AIaW
@NitroRCr·TypeScript
Manage multi-workspace AI chats, tools, and synced data across platforms.
Project overview
AIaW is a local-first AI chat client with multiple workspaces, support for several model providers, MCP connections, plugins, reusable prompts, and editable Artifacts. Conversation data is stored locally for offline access, with optional cloud synchronization after sign-in across Windows, Linux, macOS, Android, and the web PWA. The project is deprecated and has been replaced by the rewritten Nya AI client, so existing users are directed to migrate rather than adopt AIaW as a new long-term setup.
Keinsaas Navigator is an open-source AI workspace for individuals and teams. It combines multi-provider chat with custom agents, MCP tools, visual workflows, and optional capabilities such as image generation, code execution, and realtime voice interaction. The application can run locally, in Docker, or on Vercel. A model-provider API key is the minimum requirement, while features such as web search, file storage, or particular integrations need their own service configuration.
Use local models, cloud APIs, and personal knowledge bases from one AI assistant.
Project overview
AingDesk is a desktop and server AI assistant that brings local models, mainstream model APIs, and local knowledge bases into one interface. Users can build agents, search the web, connect MCP services, and share configured assistants for others to use. Desktop releases are available for macOS and Windows, while the server edition can run with Docker; users still need to install local models or configure the relevant provider credentials.
Run page-aware AI tasks with multiple models, Agent Skills, and MCP from a browser sidebar.
Project overview
Tactus is a browser extension for Chrome, with a temporary Firefox debug-install path, that combines AI chat, page extraction, Agent Skills, and HTTP MCP tools in a sidebar. Users can import skills with instructions, scripts, and resources so the agent can understand the current page, call external tools, and automate repeatable workflows; first-time script execution requires confirmation. Conversation history and skill files are stored locally, but model and MCP calls still connect to user-configured external services through endpoints, credentials, or OAuth.
Runs an open-source terminal coding agent with swappable providers, subagents, MCP, and client integrations.
Project overview
Qwen Code is an open-source coding agent for the terminal with Auto-Memory, Auto-Skills, subagents, agent teams, and MCP. It supports interactive and headless use, an experimental shared daemon, and providers using OpenAI, Anthropic, Gemini, Qwen, or local-model-compatible APIs. The project also ships IDE, desktop, SDK, and IM integrations; Node.js 22 or newer is required for the npm installation path.
grok-cli connects a terminal coding agent to xAI’s Grok API, with web and X search, sub-agents, and Telegram control while the CLI keeps running. It offers an interactive terminal UI plus a headless prompt mode. A Grok API key is required, and the community project is not affiliated with or endorsed by xAI.
Coding agentSoftware developmentLanguage Server Protocol
copilot-cli
@github·Shell
Handle coding and GitHub tasks conversationally from your terminal.
Project overview
GitHub Copilot CLI brings its coding agent into a local command-line workflow for building, editing, debugging, and refactoring code. It can also work with repositories, issues, and pull requests through an authenticated GitHub account and extend its tools through MCP servers. Actions are previewed for approval, and use requires an active Copilot subscription with prompts counting against premium-request quotas.
Run a local Codex fork with browser tools and multiple agents
Project overview
Every Code is a community fork of OpenAI Codex for local terminal development. It extends the upstream tool with browser actions and multi-agent workflows, while Auto Drive and background Auto Review support longer execution and non-blocking checks. It supports ChatGPT sign-in or API-key use, can orchestrate external CLIs such as Claude and Gemini, and is not an official OpenAI product.
Run models and tools in a small, permission-aware terminal agent
Project overview
San is a native Go terminal harness distributed as a single binary of roughly 12 MB. It lets you switch models and search backends, attach plugins or MCP servers, and control actions through ask, auto-accept, or autopilot modes. Sessions can resume or fork, and a local inspector can replay transcripts; provider credentials are still required for the services you choose.
Work with Mistral models through a conversational coding CLI
Project overview
Mistral Vibe is Mistral's open-source command-line coding assistant for exploring, searching, and editing projects through natural language while running shell commands when needed. It supports delegated subagent tasks, reusable skills, and selectable agent profiles; voice input is experimental, and Unix environments are the official target even though Windows can run it.
General agentPersonal and daily lifeCLI integration
hermes-agent
@NousResearch·Python
Run a self-improving agent across sessions and remote machines
Project overview
Hermes Agent is designed to retain useful context across sessions by creating skills from experience, searching past conversations, and nudging knowledge to persist. It can run on a small VPS, a GPU cluster, or serverless infrastructure, and Telegram access lets you interact with a cloud instance while it works away from your laptop.
Agent harnessAI and agent developmentModel Context Protocol
deepagents
@langchain-ai·Python
Build extensible agents for long-running, multi-step work
Project overview
Deep Agents is an agent harness for long-running, multi-step work, with built-in planning, sub-agents, filesystem access, shell use, and persistence. Each part can be overridden or replaced without forking, and the framework can work with tool-calling frontier, open-weight, or local models.
Build multi-agent, sandbox, and realtime voice workflows in JavaScript
Project overview
The OpenAI Agents SDK organizes agent workflows around tools, guardrails, handoffs, sessions, and tracing. It also includes sandbox agents for filesystem work and realtime agents for low-latency voice interactions, with support for Node.js, Deno, and Bun. Sandbox agents are marked beta, and browser voice sessions should use a server-created ephemeral client token rather than exposing a long-lived API key.