Free AI Tools for Open Source

Rewisp is an on-device ambient memory for Mac that captures text from your screen and lets you ask anything about your past activity, automatically surfacing promises, changes, and summaries while keeping everything private.

Open-source platform for real-time AI agent security, auditing skills and runtime with community-driven threat rules.

OpenSEO is an open source SEO platform that integrates with AI agents via MCP to provide real SEO data for keyword research, competitor analysis, backlinks, and more.

An open-source cost controller for AI agent loops that stops loops when converged and rolls back before degradation.

A specialized local inference engine for large language models, optimized for Apple Silicon and SSD streaming on memory-constrained systems.

Open-source tool running specialized AI agents to review code, sync docs, perform deep QA testing, and distill repository knowledge on a schedule.

Open-source CLI, debug agents, and browser tools for building and maintaining reliable web integrations.

Local-first AI operator that controls your Windows PC, files, shell, apps, browser, and desktop, with voice and memory, all on your machine.

Wolbarg is a local-first TypeScript SDK providing shared semantic memory for AI agents using SQLite or PostgreSQL.

An open-source Python framework for building agentic AI applications with server-driven UI, native observability, sandboxing, and pluggable model orchestration.

Rewisp is an on-device ambient memory for Mac that captures text from your screen and lets you ask anything about your past activity, automatically surfacing promises, changes, and summaries while keeping everything private.

Open-source platform for real-time AI agent security, auditing skills and runtime with community-driven threat rules.

OpenSEO is an open source SEO platform that integrates with AI agents via MCP to provide real SEO data for keyword research, competitor analysis, backlinks, and more.

An open-source cost controller for AI agent loops that stops loops when converged and rolls back before degradation.

A specialized local inference engine for large language models, optimized for Apple Silicon and SSD streaming on memory-constrained systems.

Open-source tool running specialized AI agents to review code, sync docs, perform deep QA testing, and distill repository knowledge on a schedule.

Open-source CLI, debug agents, and browser tools for building and maintaining reliable web integrations.

Local-first AI operator that controls your Windows PC, files, shell, apps, browser, and desktop, with voice and memory, all on your machine.

Wolbarg is a local-first TypeScript SDK providing shared semantic memory for AI agents using SQLite or PostgreSQL.

An open-source Python framework for building agentic AI applications with server-driven UI, native observability, sandboxing, and pluggable model orchestration.

PokeTokenBar turns your AI coding tokens into a Pokémon companion in the macOS menu bar, tracking usage and gamifying evolution.

Open-source AI app builder that turns a prompt into a full-stack Next.js web app with built-in hosting, sandbox, database, auth, and more.

An open-source QA agent that reads codebases, derives business flows, and runs end-to-end tests across frontend and backend.

Open-source context engineering layer for AI agents that reduces token usage by ~80% and improves accuracy by selectively providing relevant tools and skills.

Nous centralizes the data scattered across your GTM tools into one context graph, resolving every person and company into a single record your agents read in one call.

Paste a public domain to get scroll-stopping, on-brand ads in seconds.

Open-source PR alignment reviewer that checks whether every GitHub PR matches the linked Linear issue and sprint intent before merge.

Disposable, network-restricted Linux VMs for AI coding agents — give each agent its own machine instead of yours.

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.