AI Open Source

Signup

Go to: All AI Tools AI Tools by Tool Type AI Tools by Job Type

AI Open Source

Explore top-tier open-source AI tools, freely accessible and highly customizable. Leverage active communities, transparent development, and powerful algorithms to implement state-of-the-art solutions without licensing constraints.

Signup & Stay Updated on the latest AI Tools

AI Open Source

### AI Tools available

oMLX

oMLX caches KV data to SSD, letting local AI models resume prior conversations in milliseconds, even after a restart. It is built for developers running models on Macs who want faster, more responsive agent interactions without full recomputation.

Hy4 preview

Hy4 preview is a large language model from Tencent designed for long-horizon agentic tasks. It autonomously handles coding, game development, and complex document analysis, running tests and fixing bugs before delivering results. It is intended fo...

Staats

Staats is a web analytics script and MCP server that lets coding agents read live traffic and interaction data inside your chat. It is for developers who want their agents to check performance data proactively, warning them before changing feature...

Warren

Warren turns coding-agent runs into operational workloads that run beyond a developer terminal. It handles workspaces, run dispatch, limits, event history, recovery, and delivery, and is built for developers and teams running agent harnesses like ...

TaskShell 2.0

TaskShell 2.0 is a Model Context Protocol server that connects task management tools with AI coding agents such as Claude Code, Cursor, and OpenCode. It lets users add todos from conversations, check due dates, prioritize work, and share relevant ...

session-indexer

session-indexer creates a per-project SQLite index of Claude Code session history, searchable by semantic similarity via bge-m3 with an automatic FTS5 keyword fallback. It is for developers who need to recall past decisions across long-running pro...

KerasFormers

KerasFormers is a library for running Hugging Face model architectures in Keras 3, supporting over 60 vision, speech, large language, and vision-language models. It provides weight conversion and parity checks so users can work across TensorFlow, ...

Flunkey

Flunkey is a time and cost-saving AI tool currently in beta. It is designed for individuals and teams seeking to reduce manual effort in their workflows, helping them complete tasks more efficiently.

fx (by Vercel)

fx is an open-source coding agent from Vercel, distributed as a roughly 6MB binary that starts quickly and uses minimal memory. It is designed for developers who want a lightweight, model-agnostic alternative to full IDEs, supporting local or clou...

OneCLI

OneCLI is an open-source agent harness for teams that gives each employee a sandboxed AI agent connected to GitHub, Gmail, Notion, Dropbox, or a CRM. Agents never hold real secrets; a gateway injects credentials at the network layer after human ap...

Cronloop AI

Cronloop AI runs scheduled autonomous agents that use your existing Claude Code or Codex subscription to execute recurring tasks. It is for developers and builders who want AI agents to work continuously, such as curating event websites, doing dai...

anyCreature by Gobkit

anyCreature by Gobkit is an open-source, mesh-based generative harness for technical artists and game developers. It checks 3D models against automated quality control standards, quantified aesthetic criteria, and silhouette readability tests, and...

OpenTrade

OpenTrade is an open-source macOS app for managing Claude Code and Codex agents that trade through Robinhood. It provides monitoring, background sessions, per-agent guardrails, and order approvals to help users supervise multiple AI agents on thei...

Blender Agent Bridge

Blender Agent Bridge lets AI assistants work inside Blender by inspecting scenes, gathering viewport and render evidence, and using structured tools for longer workflows. It is built for Blender users, technical artists, and developers of MCP-base...

Inferock Bench

Inferock Bench is a diagnostic tool for AI developers that analyzes tool-call failures and retries in LLM workflows. It reports which calls failed, how retries behaved, and flags patterns like silent data corruption where a call returns success bu...

Phinq

Phinq is an open-source governance layer that sits between AI agents and their actions, classifying risk before execution and pausing irreversible operations for human approval. It enforces user-defined rules and logs all activity for audit. It is...

Munder Difflin

Munder Difflin is a free, open-source PC app that runs a local office of persistent AI agents, using tools like Claude Code and Codex to automate tasks on your computer. It is for users who want to delegate work to a supervised or autonomous AI cl...

Treg

Treg is a pay-per-call API proxy for AI agents, providing access to 2,600 tools across roughly 40 providers for tasks like SEO, social media, and lead enrichment. It handles OAuth setup and credential injection for agents, and is open source under...

apra-fleet

apra-fleet is a control plane that runs AI agents across your own machines and multiple AI providers, coordinating long-running work like software delivery. It is for teams that want to run unattended AI workflows across their existing infrastruct...

CodeBurn

CodeBurn is an open-source cost analytics tool that reads session logs from AI coding tools like Claude Code and Cursor. It breaks down spending by task, model, project, and pull request, helping developers and teams identify waste and optimize th...

Gotcha

Gotcha is an open-source AI co-pilot for Android that automates tasks through UI control and terminal access. It targets users who want a local, privacy-focused assistant capable of executing commands, scripts, and app interactions without relying...

Prime Agent

Prime Agent is an open-source, self-improving coding harness for AI developers and researchers. It uses Recursive Language Model and Continual Harness abstractions to advance agent performance, achieving 95.5% on ARC-AGI-3 with Opus 5, above the r...

Open Index

Open Index provides a structured context layer for AI agents by defining entities and their relationships. It helps developers in domains like security and legal build agents that can navigate complex information graphs effectively.

Soup CLI

Soup CLI is a command-line tool for fine-tuning large language models on computers with limited GPU memory. It streams frozen base model layers from system RAM during LoRA training, allowing models that exceed GPU capacity to be trained. It is int...

bb

bb is an open-source agentic orchestrator GUI for Claude Code, Codex, OpenCode, Cursor, and other ACP-compatible agents. It is for developers who want to customize their agent workflows, as nearly every component can be changed or extended with pr...

Toolport

Toolport is a free, open-source local MCP gateway that lets multiple AI agents share the same configured servers. It reduces token usage by up to 91% through on-demand tool searches. It is for developers using Claude, Cursor, VS Code, Codex, or ot...

BrowserOS neo

BrowserOS neo is a secondary browser designed for AI agents as a local browser for your agents with one click, a secondary browser that runs locally. The tool is a local browser that runs locally. BrowserOS neo, the secondary browser built for use...

HAR

HAR provides a single in-repo contract that centralizes configuration and documentation for AI agents. It targets development teams managing multi-agent setups, replacing scattered CLAUDE.md files, README instructions, editor rules, and CI config ...

Keystroke

Keystroke is a collaborative platform for building, deploying, and running AI agents inside a company. It provides integrations, credentials, memory, workflows, triggers, approvals, and observability in one workspace, allowing teams to create agen...

Finyuus

Finyuus is a domain-specific language for composing AI workflows, backed by Temporal for durable execution. It lets developers define, version, and operate agents, prompts, tools, and guards independently from application code, using a dashboard f...

Hexis

Hexis is a centralized platform for managing a company's AI skills, tools, and knowledge, built on top of Git for versioning and review. It provides access controls for admins and lets employees use these assets from any AI agent via MCP.

SpeakoFlow

SpeakoFlow is a voice layer for your desktop that lets you dictate text into any app and use voice commands to perform actions. It includes a local speech-to-text engine and an optional on-device assistant. Designed for anyone who wants to control...

npm i -g hotcell

Hotcell is an open-source command-line tool that creates, pauses, and manages isolated sandboxes on local hardware, including laptops, Linux VMs, and bare metal. It is built for developers and agentic coding tools, supporting Docker, Apple VZ, or ...

mpai

mpai shares a Claude Code or Codex session over Tailscale, letting teammates send attributed prompts into the same terminal conversation. It is for developers who want to collaborate in a coding session that was previously single-player.

agent-manager

agent-manager is a keyboard-driven tool for running coding agents inside tmux sessions, letting users start, review, and fork agent work with single keypresses. It is built for developers who use multiple CLI coding agents and want to keep their s...

AgentConnect

AgentConnect is an open-source platform that lets teams run Claude Code, Codex, or any ACP runtime inside Slack, Discord, Telegram, and GitHub. It is for teams that want to share, take over, and reuse agent sessions across their existing tools whi...

Aegisora

Aegisora is an open-source runtime security proxy for AI agents. It gives engineering and security teams zero-trust control over agent actions in production, blocking semantic prompt injections, unauthorized API calls, and PII leaks.

Prompt Golf

Prompt Golf is a free, open-source game where players test their prompting skills by getting an AI model to output specific target phrases using the fewest characters and messages. It is designed for AI enthusiasts who want to practice and compare...

Premation

Premation is an open-source, AI-native motion design tool for creators and developers. It allows users to customize motion graphics workflows and collaborate on platform extensions.

Yap

Yap converts speech to text locally for developers. This free, open-source macOS dictation tool uses Apple's on-device SpeechAnalyzer API, requiring no network calls or large models.

Greplica

Greplica provides shared, self-updating wikis for developer teams, managed by coding agents. It anchors tribal knowledge in committed code and uses multi-tier retrieval to supply relevant context to language models.

Meterless.ai

Meterless.ai lets you keep the work AI does during a chat session, not just the final answer. It is for anyone who uses AI for research, planning, coding, or file organization and wants to edit or rerun those tasks with cheaper models.

AI YC interview with Gstack agents

Gstack joins Google Meet as AI voice bots to simulate YC partner interviews. It uses your local coding agent to process transcripts. The tool is for developers testing agents in live meetings.

Memmy Agent

Memmy Agent manages memory and context for developers using coding assistants like Claude Code. It allows programmers to maintain project details across multiple coding sessions.

HOL Guard

HOL Guard protects AI agents from prompt injection, secret exfiltration, and malicious packages. This open-source security tool uses heuristics to help developers prevent autonomous agents from executing catastrophic actions on host systems.

AgentLoop

AgentLoop manages execution loops for artificial intelligence agents. It provides developers with a framework to build autonomous systems that complete multi-step tasks using large language models.

Paritok

Paritok is a compression gateway that sits between coding agents and their API to reduce token usage. It shrinks tool schemas, compresses file reads and outputs, and summarizes stale history, cutting token bills by 25% to over 85% in long sessions...

BaseRT

BaseRT runs local language models for Apple Silicon users. This LLM runtime allows them to install and execute models directly on their own devices with a single command.

Inbix

Inbix is a developer-first email platform built for automation, testing, and AI agents. It lets engineers create inboxes via API and trigger webhooks to receive emails in real time.

iMessage Hermes on a Raspberry Pi

iMessage Hermes on a Raspberry Pi is an always-on AI agent that users text via iMessage or SMS. It serves developers and families building custom home automation and scheduling tools.

WebBrain

WebBrain is a free, open-source AI browser agent that operates directly inside the browser. It is designed for users who want an autonomous assistant for web tasks without being tied to specific models or subscription fees.

Sim

Sim is an open-source workspace to build agentic workflows. It enables teams to connect AI agents and workflows to 1,000+ integrations and LLMs.

Osaurus

Osaurus is an open source AI agent platform that runs locally on Mac computers for users who want to keep their data private. It allows agents to interact with local files and applications without using external servers.

LongCat-2.0

LongCat-2.0 is an MIT-licensed MoE model trained for coding and agentic workflows. It provides developers with a one million token context and integrates with Claude Code and OpenClaw.

Nixmac

Nixmac is a shell script that manages Nix system configurations for non-technical users. It allows people without computer expertise to maintain their devices without asking a tech-savvy friend for help.

Livinity

Livinity is a homeserver operating system that provides a dashboard for Docker apps and a built-in AI assistant. It helps sysadmins install containers and automate tasks while keeping data on their hardware.

PMB

PMB provides developers with local memory for coding agents by storing decisions and lessons in a SQLite workspace. It feeds this context to tools like Cursor and Claude Code to prevent repeating instructions across sessions.

Heron

Heron is a passive analyzer that reconstructs AI agent actions from network traffic for engineering teams. It captures LLM traffic and stitches multi-call interactions into agent turns for debugging without requiring proxies.

Laguna by Poolside

Laguna M.1 is an open weights AI model with 23B active parameters and a 256K context window. It allows developers to run, evaluate, fine-tune, and build directly on their own infrastructure.

Foglamp

Foglamp provides AI agent developers with observability into cost, latency, token usage, and distributed traces with replay. It also offers automated evals and alerts for spend spikes or failures.

Darkmoon

Darkmoon is an open-source, self-hosted autonomous penetration testing platform. It employs specialized methodology agents and integrated offensive security tools to assess Active Directory, Kubernetes, and cloud environments for professional pent...

CADAM

CADAM is an open source Text to CAD platform for makers. It generates mechanical designs by converting text prompts into code. Users can build models programmatically.

whoburnedmore

Whoburnedmore is a command-line tool that tracks token usage, costs, and active days across AI coding tools. It provides developers with a personal dashboard and a public leaderboard to compare compute metrics.

Deep Work Plan

Deep Work Plan prevents AI agents from drifting during long coding tasks by storing specs and acceptance criteria directly in the repository. It gives developers a tool-agnostic way to maintain context without relying on chat windows.

Memoriq

Memoriq is an open-source, end-to-end encrypted AI memory for users managing conversations across multiple AI models. It provides a self-hosted or hosted service so your chats remain private and accessible only to you.

MindReader v1

MindReader v1 simulates second-by-second how a brain responds to content. It feeds TRIBEv2 data into a neuro-analyst agent to analyze seven dimensions like attention. Marketers can use it to evaluate social media posts.

Timmy-TUI

Timmy-TUI makes local AI agent workflows inspectable: capture model choice, tool evidence, filesystem context, workspace launch, logs and sealed MCP→CLI receipts with manifest hashes-open-source, local-first.

AgentOS

AgentOS centralizes AI agent operations in a local-first control surface: organize workspaces, agents, tasks, models, sessions, approvals, onboarding, and runtime visibility for builders and solo founders.

PandaProbe Cloud

PandaProbe Cloud provides full-stack tracing, evals, and monitoring for agents. It is for AI engineers and platform teams debugging agent behavior and tracking quality without managing infrastructure.

agmsg

agmsg lets CLI AI agents (Claude, Codex, Gemini, Copilot) exchange messages via a shared SQLite file. Vendor-agnostic, persistent, and dependency-light (bash+SQLite). No daemon or network-run unattended agent-to-agent workflows.

Agent Browser Shield

Agent Browser Shield: free, source-available browser extension that strips hidden prompt injections, trackers, cookie banners and noisy page elements so browser-based AI agents see only clean content, reducing attack surface and token waste.

Keen Code

Keen Code is an open-source CLI coding agent in Go. It uses agent-built workflows, distilled turn memory to limit multi-turn context, and skills-driven MCP tools that fetch JSON schemas on demand for efficient, transparent code generation.

Skybridge

Skybridge is an open-source framework for developers building MCP apps for AI hosts like Claude and ChatGPT. It abstracts implementation differences so the same code runs across multiple clients.

Hermes Desktop

Hermes Desktop is an open-source AI agent that grows with you. Native macOS, Windows and Linux app for automating workflows, managing tasks and research pipelines. By Nous Research.

EchoFlow

EchoFlow: an open-source, BYOK AI chat built for Android-native Material UI, local encrypted conversations stored on-device for offline access, no tracking or cloud history.

Second Brain for AI

Second Brain for AI: semantic memory retrieval with deduplication and adaptive summarization. Fetch or compress context smartly, with adjustable similarity thresholds to merge overlapping notes and keep multi-step AI tasks within context limits.

Wallie V2

Wallie V2 is an open-source AI streamer that reacts to your screen and live chat, remembers topics across sessions, animates Live2D with natural lipsync, and runs locally so your API keys stay private.

Wandesk

Wandesk is an AI desktop that builds working apps on your computer from plain descriptions-calorie trackers, invoice generators, reading lists-keeps them with chat, files, tasks and memory, and is 100% local, free, and requires no account.

Parastore

Parastore simulates synthetic shoppers in 3D store layouts: they browse, pick items, impulsively buy near checkout, and generate revenue and behavioral data. Open-source (MIT) framework for layout testing and agent-based retail research.

Crew44

Crew44 is a local-first command center that turns the AI coding agents on your machine into a coordinated team. Create role-based specialists, assign runtimes, share workspace memory and handoffs, no account required, MIT licensed.

Harbor

Harbor runs and auto-wires local AI services with one command. Start frontends, LLM backends, search, voice and more from a 129-service catalog; includes agent launch and an OpenAI-compatible local API.

Phasr

Phasr centralizes engineering workflows: run 100+ persistent workspaces, manage multiple repositories, pin key commands, and coordinate AI agents-reducing context switches so teams stay organized and move faster.

Pi Coding Agent

Pi Coding Agent is a minimal, hackable terminal harness for building and customizing AI coding-agent workflows. Keep the core small and extend or replace context management, sub-agents, permissions and workflows via extensions.

DecisionBox for Databricks

DecisionBox for Databricks connects to your workspace, auto-writes SQL, validates findings against your data, and delivers a ranked backlog of verified, prompt-free insights. Read-only, Unity Catalog scoped; supports Serverless, Pro, Classic SQL w...

MartinLoop

MartinLoop is an open-source control layer for coding agents that enforces hard budget caps, verifier-gated retries, scope/secret safety, rollback evidence, and JSONL run logs-keeping autonomous runs fast and accountable.

CLI Market

CLI Market is a Python connector that maps VTEX storefront APIs into one JSON schema. Query products across retailers (Carrefour BR, Sainsbury's UK, Wong PE) for programmatic and AI-agent access. Open-source MIT; pip install cli-market

AgentRail

AgentRail: an open-source task lifecycle API that turns GitHub Issues and Linear tickets into routable tasks, delivers structured CI summaries, ranks PR comments by severity, and enforces per-agent scoped keys; runs locally, free to self-host.

Standboy

Standboy is a Game Boy in your editor sidebar that wakes when your AI agent runs and hides when it stops. Play GB/GBC/GBA ROMs with saves stored locally. Free, MIT-licensed, no telemetry.

Gradient Bang

Gradient Bang: an open-source, massively multiplayer LLM-driven space trading game. Talk to and manage ship AIs, design sub-agents in a Vercel sandbox, handle long LLM contexts, and compete on live leaderboards.

Mi

Mi is a 30-line agentic loop with two tools and an LLM plug-in-compact, optimized for local LLMs, token-efficient, and featuring sandbox mode to run in a container for safer, isolated execution.

ShioriCode

ShioriCode: a desktop UI for coding-agent CLIs that keeps each run as a project-aware thread tied to branch/workspace, streams activity into a timeline, and previews generated diffs without leaving the app. Supports any authed CLI or Shiori host.

Linchpin

Linchpin is an open-source runtime for hosting managed agents on a single VM: per-session Docker sandboxes, persistent event logs, HTTP/SSE API, built-in tools and encrypted credential vaults for quick self-hosting.

Agentmemory

AgentMemory gives AI coding agents persistent cross-session memory: it captures agent activity, compresses it into structured memories, indexes via hybrid search, and injects relevant context. 100% open source.

Memori

Memori captures AI agent traces and tool results into structured, persistent memory-enabling scoped, async recall, automated daily briefs, and reduced prompt bloat across projects.

Pipali

Pipali is a desktop AI coworker that automates work: research files and the web, draft briefs, spreadsheets, emails, reports and personal apps, run recurring tasks and monitor events with sandboxed permissions.

OpenHuman

OpenHuman: a privacy-first AI agent with two-minute setup and one-click Gmail/Slack/Telegram/Notion/GitHub connections. Runs locally with encrypted, persistent memory. Open-source and free to start.

Radar

Radar is an open-source, local-first Kubernetes UI that consolidates cluster workflows: ownership-aware topology, live watches, Helm + GitOps, traffic flows, cost insights and audits-no signup required.

Gas City 1.0

Gas City 1.0 is a software factory that runs coding agents to deliver enterprise-grade features, quality and schedule-accelerating development for large-scale projects while preserving production standards.

Gas City 1.0

Gas City 1.0 is a software factory that runs coding agents to deliver enterprise-grade features, quality and schedule-accelerating development for large-scale projects while preserving production standards.

.

As seen on