Tag
45 catalogue entries use this topic; each Project's license policy is labeled separately.
AI coding agent for terminal, editor, and desktop
OpenCode is an MIT-licensed AI coding agent available through terminal, desktop, and IDE clients. It supports hosted providers and local models. Code handling depends on the selected provider; optional session sharing uploads conversation history to OpenCode's sharing service.
Run open language models locally with one command
Ollama reduced local model hosting from an afternoon of CUDA troubleshooting to a single pull command. It handles model download, quantisation selection, GPU offloading, and memory management, and exposes an OpenAI-compatible endpoint on localhost.
Turn any website into clean, model-ready data
Firecrawl handles the unglamorous part of feeding the web to a language model: rendering JavaScript, following pagination, stripping navigation and cookie banners, and returning markdown or structured JSON that a model can actually use.
One chat interface for every model you run or connect
Open WebUI is the front end that turns a local inference server into something a household or a team can actually use. It handles accounts, conversation history, document retrieval, and model switching, and speaks to both local runtimes and hosted APIs.
Inference engine that runs LLMs on almost any hardware
llama.cpp is the layer most local model tooling is built on. It is a C and C++ inference engine with no Python runtime, aggressive quantisation support, and hand-tuned kernels for a remarkably wide range of hardware.
Autonomous agents that complete real engineering tasks
OpenHands runs agents that plan and execute multi-step engineering work: reading a repository, editing files, running tests, and iterating until a task is done. Each agent works inside a sandboxed runtime rather than on the host machine.
Open-source web crawler that turns pages into LLM-ready markdown
Crawl4AI is a Python crawler that turns websites into clean markdown and typed JSON for RAG pipelines, AI agents, and data pipelines.
Polished chat interface for many model providers
LobeChat is the most designed of the open chat front ends. Plugins, an assistant marketplace, voice input and output, and vision support are all present, and the interface holds up next to commercial products.
Private desktop chatbot that runs open LLMs fully on-device
GPT4All is a free desktop app from Nomic that runs open language models entirely on your own computer, with no cloud calls.
Open-source AI coding agent for VS Code, JetBrains, and the terminal
Cline is an open-source AI coding agent that reads, edits, and runs code inside VS Code, JetBrains IDEs, and the terminal.
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.
Open-source AI gateway unifying 100+ LLMs behind one API
LiteLLM is an open-source AI gateway that calls more than 100 large language model providers through one OpenAI-compatible interface.
Desktop AI chat client for cloud and local models in one place
Cherry Studio is a desktop chat client for cloud and local models in one interface. It runs on Windows, macOS, and Linux, and stores data on the local machine.
Self-hosted OpenAI-compatible runtime for local AI models
LocalAI is a self-hosted runtime that runs AI models locally behind OpenAI-compatible endpoints.
Terminal pair-programming assistant that edits codebases with LLMs
Aider is a terminal-based pair-programming tool that applies LLM-suggested edits directly to files in new or existing codebases.
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 AI coding assistant for VS Code and JetBrains
Continue is an open-source AI code assistant for VS Code, JetBrains, and the terminal.
Self-hostable platform for RAG knowledge bases and visual AI workflows
FastGPT is a self-hostable platform for RAG knowledge bases and visual AI workflows, combining document processing and retrieval with flow-based app orchestration.
Open-source AI coding agent in the IDE, CLI, and cloud
Kilo is an open-source AI coding agent that works inside VS Code, JetBrains IDEs, and Visual Studio, with a command-line build and a cloud runner on the way. It reads the existing codebase and carries out engineering tasks from natural-language instructions, proposing file edits, running commands, and verifying its own work.
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 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.
Local, open-source AI app builder that turns prompts into ownable code
Dyad is a local-first AI app builder that turns natural-language prompts into working web applications, with the generated code stored on your own machine.
Open source coding agent that fixes GitHub issues with LLMs
SWE-agent is an open source coding agent that turns a GitHub issue into a tested fix by letting a language model use shell, editor, and search tools in a sandbox.
A control layer for customer-facing AI agents
Parlant addresses the problem that stops most support agents from shipping: a model that is helpful ninety-five percent of the time is not safe to put in front of customers. It manages behaviour through explicit, context-matched guidelines rather than one long prompt.
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.
Open-source AI gateway routing 200+ providers with fallbacks
Portkey AI Gateway is an open-source gateway that routes app traffic across 200+ LLM providers with fallbacks, load balancing, caching, and guardrails.
Open-source AI answer engine with a generative UI
Morphic is an open-source AI search engine that answers questions with complete, cited responses instead of link lists, using Quick and Adaptive search modes in a self-hosted app.
Self-hosted LLM gateway with one OpenAI-compatible API
Bifrost is a self-hosted gateway that puts every large language model call behind one OpenAI-compatible API. An application points its existing OpenAI client at the gateway, and Bifrost routes the request to whichever provider is configured, so switching models or spreading load across providers is a configuration change rather than a rewrite.
Terminal AI coding harness with ZSH prompts and per-task model choice
Forgecode is a terminal-native AI coding harness that reads, edits, and runs code from ZSH with muse, forge, and sage agents.
Private AI chat with zero-access encrypted history
Proton Lumo is a privacy-first AI chat assistant that stores conversations with zero-access encryption, keeps no logs, and never uses chats to train models.
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.
Private offline AI chat with on-device LLMs for iPhone and Mac
Fullmoon is a free app that chats with small open language models running entirely on your iPhone, iPad, or Mac, with no account and nothing sent to the cloud.
Self-hosted AI gateway routing LLM traffic through Envoy
Envoy AI Gateway is a self-hosted gateway that routes application traffic to 17 language model providers through one OpenAI-compatible API.
Local-first desktop workspace for coding-agent runtimes
Synara is a free, open-source, local-first desktop workspace that hosts coding-agent sessions with projects, terminals, diffs, and Git delivery in one app.
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.
Open-source Markdown that mounts interactive apps for LLMs
MDMA is an MIT-licensed open-source framework by Mobile Reality that turns LLM Markdown output into interactive applications with forms, tables, and approval gates.
Open-source AI gateway that traces, evaluates, and protects LLM calls
Grepture is an open-source AI gateway that sits between an app and its LLM providers to trace, evaluate, and protect every call.
Open-source proxy securing AI API keys in iOS apps with DeviceCheck
Proxed AI is an open-source proxy that keeps AI API keys off iOS devices, checking each request with Apple DeviceCheck while adding rate limits and usage tracking.
Open-source, OpenAI-compatible LLM gateway with cost and latency tracking
LLM Gateway is an open-source gateway that puts OpenAI, Anthropic, and Gemini calls behind one OpenAI-compatible API. An application keeps its existing OpenAI client and points it at the gateway, so switching providers or spreading load across them is a configuration change rather than a rewrite.
OpenAI's assistant and the interface that set the pattern
ChatGPT is the product that made conversational assistants ordinary. Beyond the chat box it now covers file analysis, image generation, web browsing, voice, and custom assistants sharing one account.
Anthropic's assistant, strongest on long documents and code
Claude is positioned around careful reasoning over long inputs. The large context window makes whole-repository and long-document work practical in a way that shorter context assistants cannot match.
An editor rebuilt around model assisted editing
Cursor forked VS Code rather than extending it, which let it change the editing model itself. Multi-file edits, codebase-wide context, and a tab completion that predicts the next edit rather than the next token are the result.
AI completion and chat inside the editor
Copilot put model assisted completion in front of a very large number of developers first, and inline suggestion in the editor remains the interaction most people mean by AI coding.
Desktop application for running language models locally
LM Studio made local models approachable for people who do not want a terminal. Browse a catalogue, download a quantisation that fits the machine, and chat, with hardware requirements explained in plain language.