AI coding assistant with deep codebase context. Indexes your entire repo graph for accurate answers. VS Code and JetBrains extensions. Enterprise plan from $16K per year.
Cody is Sourcegraph's AI coding assistant, and its core advantage is context. While most AI tools only see the files you have open, Cody indexes your entire codebase and uses Sourcegraph's code graph to pull in the most relevant context for every query. It understands cross-repository dependencies, function call chains, and type hierarchies. This makes it significantly more accurate for questions about large, complex codebases where the answer depends on code you are not currently looking at. It supports Claude and GPT models, runs in VS Code and JetBrains, and offers autocomplete, chat, inline edits, and custom commands. Cody is now sold as an enterprise product only - plans start at $16K per year on an annual contract, so there is no self-serve free tier for individuals anymore.
Last verified
npm install -g @sourcegraph/codySources: Cody docs, Sourcegraph pricing, Install Cody CLI, Installing Cody in VS Code, Cody supported LLMs, Sourcegraph changelog, Automatic provider failover
Open-source AI code assistant for VS Code and JetBrains. Bring your own model - local or API. Tab autocomplete, chat, inline edit. Fully customizable.
GitHub's AI coding assistant. Inline completions, chat, and agent mode in VS Code and JetBrains, plus a coding agent that turns issues into pull requests. Free tier, Pro from $10/mo.
Open-source autonomous coding agent inside VS Code. Creates files, runs commands, and can use a browser for UI testing and debugging with your permission.
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Defaults to Claude Opus 5.5 on paid plans as of October 2026.
AI coding assistant with deep codebase context. Indexes your entire repo graph for accurate answers. VS Code and JetBrains extensions. Enterprise plan from $16K per year.
Try Sourcegraph CodyHonest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeAnthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Defaults to Claude Opus 5.5 on paid plans as of October 2026.
AI-native code editor forked from VS Code, now sold as part of The X Subscription. Agent edits multiple files at once and Tab autocomplete predicts your next edit. Plus is $8/mo (Cursor's own Grok and Composer models only); Premium at $30/mo adds third-party models at API list price.
OpenAI's coding agent for terminal, cloud, IDE, GitHub, Slack, and Linear workflows. Reads repos, edits files, runs commands, and returns reviewable diffs.
Install Ollama and LM Studio, pull your first model, and run AI locally for coding, chat, and automation - with zero cloud dependency.
Getting StartedPrevent bloating the main conversation with research or exploration.
Claude CodeInstall the dd CLI and scaffold your first AI-powered app in under a minute: Next.js 16, Convex, Clerk, Autumn, Tailwind v4 and an agent-ready CLAUDE.md.
Getting Started
Ornith-1.0 open-source coding models explained: what "self-improving" really means, the four model sizes, hardware needs...

Qwen3.6-27B is the local coding model to benchmark first: what hardware it needs, which jobs it should take over, and wh...

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5....

Cursor 2.0 ships Composer, the first in-house Cursor coding model, and a multi-agent interface. How Composer was trained...

Kimi K2 from Moonshot AI replaced Claude Sonnet 4 in my stack - an open-source 1T-parameter MoE model that is faster, ch...

Grok Code Fast 1 is xAI's speed-optimized coding model for agentic workflows. See its pricing, where to use it, and how...

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.