Best Free AI Code Assistant tools

CodeTrain is a hands-on coding trainer that runs on your machine and teaches developers on their own codebase by having them type every line themselves.

A cooperative gate for shell commands that AI agents run, providing previews, backups, policy enforcement, and audit for tools like Claude Code and Cursor.

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.

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

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

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

Unified AI API gateway providing access to top-tier LLMs, image, video, and coding models at affordable prices.

TryCase gives your coding agent a disposable Linux desktop to run your app, test it like a user, and send back proof: screenshots, recordings, and logs.

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

CodeTrain is a hands-on coding trainer that runs on your machine and teaches developers on their own codebase by having them type every line themselves.

A cooperative gate for shell commands that AI agents run, providing previews, backups, policy enforcement, and audit for tools like Claude Code and Cursor.

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.

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

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

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

Unified AI API gateway providing access to top-tier LLMs, image, video, and coding models at affordable prices.

TryCase gives your coding agent a disposable Linux desktop to run your app, test it like a user, and send back proof: screenshots, recordings, and logs.

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

A personal blog and research site for Solidity smart contract development, offering insights and code examples.

Contextify keeps a private, searchable timeline of Claude Code and Codex sessions forever, with local AI summaries powered by Apple Intelligence.

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.

A macOS app that keeps AI agent essentials like Claude and Codex sessions, token usage, and permissions visible in your Mac notch.

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 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.

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.

Vibe-zsh is an AI-powered Oh-My-Zsh plugin that transforms natural language into shell commands using any OpenAI-compatible API.

A skill for coding agents that delegates coding, planning, review, and orchestration tasks to the zerostack CLI agent.

Open-source reliability testing harness for AI agent skills, computing pass@k scores across Claude Code, Codex, and Pi backends.

Polygraph indexes every repo you have access to and builds a graph of how they relate, enabling AI agents to plan cross-repo work without being told where to look.

Skybridge is a full-stack TypeScript framework for building type-safe MCP apps and servers with React-powered UI.

Per-block model routing CLI that sends tagged prompt sections to different LLMs for optimized AI coding workflows.

Crespo is an AI developer tool that generates compact XML blueprints of codebases using Tree-sitter AST parsing to provide LLMs with structural context.

Fully-local project memory for Claude Code that automatically captures session activity and provides a concise summary, entirely offline without API calls.

Tycoon is a platform that provides an AI CEO and a team of AI employees to help one-person companies build and grow their business automatically.

A local, zero-dependency dashboard for Claude Code that provides live token usage, context monitoring, lost-session recovery, full-text search, and phone-based approval of tool calls.

Velane is an open source AI agent code runtime that connects to your IDE via MCP, enabling autonomous creation, testing, and deployment of workflows with 800+ integrations.

ctx is a context-aware recommendation engine that dynamically selects the best skills, agents, and MCPs for your current coding task using a massive knowledge graph.

A service-boundary-aware coordination architecture for heterogeneous LLM code agents with versioned document store, pub-sub notifications, and diff-aware updates.

Conan is a native macOS app that provides a live HUD for Claude Code, surfacing prompts, tool calls, skills, and token usage in real time.

ZCode is an AI-powered coding IDE by Zhipu AI that integrates intelligent agents for planning, coding, code review, and deployment with deep reasoning capabilities.

A locally-installed developer tool that provides a senior-level AI engineering partner inside your terminal, with local-first privacy and optional cloud sync.

A local-first code-intelligence tool that turns any codebase into a queryable knowledge graph for AI coding agents.

OLO Robotics is a browser-based robotics development platform with built-in AI-assisted coding, simulation, and ROS2 tools for faster robot building.

Command Center is an agentic coding environment that helps teams ship AI-generated code to production 2x faster.

Anthropic's Claude Fable 5 is a state-of-the-art AI language model with exceptional performance in coding, analytics, vision, and research, featuring advanced safety classifiers.

Manage fleets of local and cloud agents from one surface. Plan, delegate, review, and ship without leaving your editor.

Orchids is an AI-powered app builder that lets you create web, mobile, games, CLI tools, and AI agents using natural language, leveraging your existing AI subscriptions.

OpenCode is an open source AI coding agent that helps you write code in your terminal, IDE, or desktop.

cmux is a native macOS terminal for coding agents, with tabs, panes, notifications, automation, and browser integration.

Zed is a fast, open-source code editor with multiplayer collaboration, integrated dev tools, and native AI-assisted editing.

Ghostty is a fast, GPU-accelerated terminal emulator for macOS and Linux with native UI, tabs, splits, themes, and modern terminal protocols.

Coddy.Tech is a free interactive platform for learning to code in-browser with courses, streaks, certificates, and AI help.

Qoder is an agentic AI coding platform for autonomous software development across desktop, CLI, and JetBrains IDEs.

LockedIn AI is an AI interview assistant and meeting copilot that provides real-time answers, coding help, and live coaching during interviews and calls.

Pi is a minimal terminal coding agent that customizes itself with extensions, skills, prompts, and packages.

Aider is a terminal-based AI pair programming tool that helps you build and edit code with LLMs.

CodeTrain is a hands-on coding trainer that runs on your machine and teaches developers on their own codebase by having them type every line themselves.

A cooperative gate for shell commands that AI agents run, providing previews, backups, policy enforcement, and audit for tools like Claude Code and Cursor.

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.