Free AI Tools for Open Source

Juggler is an open-source AI coding agent with a visual workbench that gives you inspectable tool calls, branching threads, and editable context for hands-on control over LLM actions on your codebase.

Unified, zero-allocation native AI inference runtime for Java, consolidating LLM, vision, and speech pipelines via Project Panama.

Osaurus is a private, local AI assistant for Mac that runs open models on-device, with optional cloud AI access and autonomous agents.

Caliber automatically generates and maintains AI context files for agents like Claude Code, Cursor, and Codex, keeping them accurate as your code evolves.

An open-source experiment that provides a SQL interface for Xarray datasets, enabling SQL queries on scientific array data.

Persistent memory for coding agents that saves discovered codebase answers and auto-deletes them when files change, reducing repeat token usage by 77%.

A forensic tool that reconstructs AI coding agent sessions from local logs to detect sensitive file reads and data exfiltration attempts.

A lean, fully-tested LLM inference server built for cheap CPU hardware, with persistent caching and an OpenAI-compatible API.

A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

Open-source AI voice agent that integrates with Asterisk/FreePBX for natural conversational IVR with cloud or local AI providers.

Juggler is an open-source AI coding agent with a visual workbench that gives you inspectable tool calls, branching threads, and editable context for hands-on control over LLM actions on your codebase.

Unified, zero-allocation native AI inference runtime for Java, consolidating LLM, vision, and speech pipelines via Project Panama.

Osaurus is a private, local AI assistant for Mac that runs open models on-device, with optional cloud AI access and autonomous agents.

Caliber automatically generates and maintains AI context files for agents like Claude Code, Cursor, and Codex, keeping them accurate as your code evolves.

An open-source experiment that provides a SQL interface for Xarray datasets, enabling SQL queries on scientific array data.

Persistent memory for coding agents that saves discovered codebase answers and auto-deletes them when files change, reducing repeat token usage by 77%.

A forensic tool that reconstructs AI coding agent sessions from local logs to detect sensitive file reads and data exfiltration attempts.

A lean, fully-tested LLM inference server built for cheap CPU hardware, with persistent caching and an OpenAI-compatible API.

A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

Open-source AI voice agent that integrates with Asterisk/FreePBX for natural conversational IVR with cloud or local AI providers.

A dependency-free C engine that streams expert weights from disk to run the 744B-parameter GLM-5.2 MoE model on consumer hardware with as little as 25 GB of RAM.

Attestor is an open-source control infrastructure that sits between AI agents and execution systems, ensuring policy compliance and safety for high-risk operations.

Open-source workspace to build, deploy, and orchestrate AI agents and workflows with visual and code tools.

Mispher turns speech into clean text anywhere on macOS, then goes further with dictation cleanup, rewrite-in-place, translation, and an on-device agent that plans, uses tools, and answers.

Aura is an open-source intelligence layer for AI coding agents that unifies multiple agents, provides AST-level diffs, and verifies changes against goals.

Open-source framework for building AI agents with flexible capabilities, tool integration, and community-driven development.

A stealth browser designed for AI agents to browse the internet seamlessly, overcoming restrictions that treat agents as second-class.

FableCut is an open-source browser video editor with a JSON timeline that AI agents can drive via MCP and REST APIs.

Frugon is a free, open-source LLM cost analyzer that identifies where your LLM bill leaks by analyzing your call logs locally.

Open Science is an open-source, model-agnostic AI workbench for scientific discovery with a coordinator agent, specialist sub-agents, and a reviewer, self-hosted for reproducibility.

Faithful, 100% local OCR Chrome extension for text, code, formulas, and tables with no hallucination.

Ghostmeet is an invisible AI meeting assistant that provides live captions and smart summaries from your browser tab, with all audio processing done locally for privacy.

An AI assistant that runs entirely in your visitor's browser, offering text chat, voice, and local RAG with zero per-message cost.

Open-source, research-grounded skill suite for humanizing AI-generated text and detecting AI writing, with nine stylometric levers derived from 50+ peer-reviewed sources.

An open, deterministic evidence layer for enterprise AI agents that grounds every claim in traceable source records and gates actions behind approval.

Tamper-evident runtime records for AI agents: hash-chained audit trail that vendors cannot edit.

CLI for AI agents to read, edit, and comment on .docx files with full format fidelity.

Open-source AI coworker for desktop that indexes your work into a living knowledge graph and provides built-in surfaces for email, meetings, browsing, and coding.

CircleChat is a team chat platform where AI agents act as teammates to plan, execute, and verify tasks with human approval on risky actions.

Skeights serializes fitted scikit-learn models to safetensors and JSON, replacing insecure pickle with a safe, inspectable format.

A self-hosted, framework-agnostic runtime for autonomous agents that records and replays every step for debugging and improvement.

Open-source security layer for AI agents enforcing RBAC, human approvals, and signed audit logs.

An open-source, OpenAI-compatible LLM gateway you run yourself, providing a single endpoint for 40+ providers with virtual keys, budgets, and usage tracking.

Let coding agents see your browser by capturing screenshots of open tabs via a CLI and browser extension.

Macro combines email, chat, docs, tasks, calls, and CRM into one open-source app with shared AI memory.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

Valmis is an open-source AI agent platform for automating business workflows securely, with isolated containers, proxy API access, and multi-step automation.

A secure file system and code execution sandbox for AI agents with built-in job queues, Docker isolation, and execution history.

A feature-rich Pomodoro timer that lives inside the Claude Code terminal, keeping focus without context switching.

A unified Python library that combines MCP servers, agent skills, custom functions, and HTTP endpoints into a single tool set for building AI agents with any LLM.

Local-first memory for AI coding agents. Automatically stores and recalls project context via MCP, offline, with ~35ms recall.

A self-hosted, browser-based AI CSV analyzer that uses multiple AI providers to analyze and visualize CSV and Excel data.

AXIOM is a bootable Rust kernel that optimizes transformer inference by replacing generic OS abstractions with inference-specific primitives.

A CLI tool that checks package versions for known vulnerabilities across npm, PyPI, and many other ecosystems, designed for AI agents to avoid using outdated packages.

Moxie is an open-source money agent that finds zombie subscriptions, duplicate charges, and missed refunds, then drafts fixes with your consent and logs every step in a tamper-evident audit trail.

An open-source ML pipeline that diagnoses car faults from audio by cleaning sound, embedding with CLAP, and training calibrated linear classifiers.

Kage is a git-native verification layer for coding agent memory that checks every claim against your code to prevent hallucinations and stale facts.

An open-source Agent UI library in VanillaJS for building agentic front-end experiences with WebMCP, SSE streaming, and customizable theming.

Open-source, privacy-first AI screen memory tool that captures and analyzes your screen activity locally to let you search and chat with your screen history.

Fleet is a local-first web console for creating, configuring, monitoring, and operating Dockerized Hermes AI agents across trusted machines.