CodeepCodeep

Autonomous coding, wherever you work

Go Deep
into Code.

One AI agent that understands your whole project, runs commands, and writes & verifies code — from your terminal, Mac, or editor.

See Codeep in actionSee the docs
CLIv3.3.0macOSv3.3.0VS Codev3.0.0
Codeep

Current task

Refactor authentication flow

Running
src/server/auth/flow.ts+142 −78
118async function authenticate(req: Request) {
119 const user = await getUser(req.headers.authorization);
120 if (!user) {
121 throw new Error('Unauthorized');
122 }
123 return user;
124 const session = await sessionService.verify(req);
125 if (!session.isValid) {
126 throw new AuthError('Unauthorized');
127 }
128 return session.user;
129}
All 48 tests passedNo failures · completed in 3.2s
Modelgpt-5.6-sol
Context1.05M · 42 files
Tokens24.7K
Cost (est.)$0.14–$0.24

Interactive product tour

One agent. Four surfaces.

The same execution story follows you from the terminal to macOS, VS Code, and the web — with every important step kept visible.

Codeep · Dashboard
Live tour
Codeep dashboard showing active sessions, usage, cost, and resource impact
Agent working

01 · Observe

Every run, visible.

Follow active sessions, token usage, cost, project activity, and estimated resource impact from one focused cockpit.

  • Live session feed
  • Cost and token trends
  • Energy and cooling estimates
Explore the Dashboard

How it works

From prompt to verified code

Codeep handles the full development loop autonomously — no context switching, no copy-pasting.

01

You describe the task

Type your request in plain language. No special syntax required. Codeep reads your project structure and key files automatically to understand the context.

input
~ $ > Refactor the auth module to use JWT tokens
02

Agent plans and executes

Codeep breaks the task into steps, executes them one by one — editing files, running commands, fetching documentation. You watch it work in real-time.

terminal
[1/4] Reading src/auth/
[2/4] Creating jwt.ts
[3/4] Updating middleware
[4/4] Running typecheck
03

Verified and ready

After making changes, Codeep runs your build, tests, or typecheck to verify everything works. If something breaks, it fixes it automatically.

output
✓ No type errors
✓ All tests pass
2 files created, 1 modified

Use cases

One command for every task

Codeep understands your codebase and executes real work — not just suggestions.

terminal
~$codeep fix the login form - validation isn't triggering on submit
▸
Scanning project — Reading src/components/LoginForm.tsx
▸
Identifying issue — Missing onSubmit handler — e.preventDefault() not called
▸
Applying fix — Patching LoginForm.tsx (2 lines)
▸
Verifying — ✓ Build passed · ✓ No type errors
✓ Fixed. The form handler was missing e.preventDefault(), causing the page to reload before validation ran.

Capabilities

Everything you need to code with AI

From autonomous agent tasks to git workflows — Codeep handles the full development loop from your terminal. Green “New” tags mark what shipped in 2.0.

Autonomous Agent

Reads files, runs shell commands, edits code, and auto-verifies the result (build / typecheck / tests) — all in one loop. You describe the goal; Codeep handles the steps.

File editsShell execAuto-verify

Sub-agents

Delegate a self-contained sub-task to a specialist that runs in its own fresh context and reports back — researcher, reviewer, tester, or your own. Keeps the main thread focused; optional auto-review after every change.

delegate/agentsAuto-review

Plan Mode

Preview the agent's full plan — files it'll touch, commands it'll run, risk it self-assesses — before any code changes. `/plan <task>` → review → `/go` to execute.

/plan/goPre-execution review

Full Project Context

Auto-scans your project structure, detects language and framework, reads key files. No manual context setup. Project memory + lifecycle hooks persist across sessions.

Auto-scan/memory.codeep/hooks/

Personalities

Switch agent tone mid-conversation: concise, verbose, security-paranoid, senior-reviewer, junior-mentor, ship-it. Or drop your own Markdown file in `.codeep/personalities/`.

6 presetsCustom .mdPer-project

User Profile

Tell Codeep how you like to work — reply language, response style, default stack, hard rules — and it adapts on every project and surface. Opt-in auto-learn picks up your preferences from sessions; sync across machines and the dashboard.

/meAuto-learnSynced
New

Approval on your phone

When a run stops on a dangerous tool it waits — and if you have walked away, it waits for as long as you are gone. Connect a Telegram bot and the same question arrives on your phone. Answer in either place; whichever comes first decides. Terminal and Mac app, on every platform.

/telegramRun / Skip / CancelNo server
New

Audit record

Every run writes down what it touched — reads and refusals, not just changes, because a capability boundary nothing records is one you take on faith. Lives with the project, shared by the CLI, the Mac app and VS Code. Paths and commands only; never file contents.

/audit.codeep/audit/Refusals

Git Workflows

AI review of your diff — bugs, security, performance, edge cases. Semantic commit messages. Works with any git repository. Hooks let you gate commits on custom checks.

/review/diff/commit

OpenRouter

100+ models from Anthropic, OpenAI, Google, Meta, DeepSeek, Mistral via one key. Authoritative cost from `usage.cost` — your dashboard sees the same numbers as your invoice.

100+ modelsReal per-call cost/openrouter

Prompt Caching

Automatic on Anthropic (and OpenRouter → Anthropic routes). Cache hits bill at 0.1× input rate; typical agent session is 60-90% cheaper. No config, just upgrade.

Anthropic60-90% cheaper/cost shows savings

MCP Marketplace

Curated catalog of 12 Model Context Protocol servers — filesystem, GitHub, Postgres, browser, Slack, more. One command install. Sampling guards keep credits safe.

12 serversstdio + HTTP/mcp install

Skill Marketplace

Write a SKILL.md (Markdown + YAML frontmatter), agent auto-invokes when triggers match. Publish to share — `/skills install <owner>/<slug>` from any machine. Claude Code-compatible.

SKILL.mdBrowse + publishAuto-invoke

VS Code & Zed (ACP)

Native agent inside VS Code and Zed via Agent Client Protocol. Same CLI binary, same commands, native diff viewer, image paste, manual confirmation mode.

VS CodeZedACP

Personal Dashboard

Link with `codeep account` to sync sessions, profiles, skills, and API keys across machines. Track cost-per-model, file bug reports, manage devices — all at codeep.dev.

Multi-device syncCost trackingBug reports

Secure & Local

API keys stored locally (encrypted at rest, synced encrypted if you opt in). Dangerous commands require confirmation. Full undo history. `/checkpoint` snapshots for safety.

Local keys/checkpoint/undo

MCP marketplace

One command, real integrations

Codeep speaks the Model Context Protocol — connect to your filesystem, GitHub, databases, browsers, Slack, anything that exposes an MCP server. Curated catalog, install with /mcp install <id>.

  • Files & Code

    Filesystem

    Read, list, and (optionally) write files in a sandbox directory.

    /mcp install filesystem
  • Files & Code

    GitHub

    Browse repositories, issues, PRs, and commits via the GitHub API.

    /mcp install github
  • Database

    PostgreSQL

    Read-only SQL access to a Postgres database — schema introspection + query.

    /mcp install postgres
  • Communication

    Slack

    Read channels, post messages, look up users and threads.

    /mcp install slack
  • Web

    Fetch (web)

    Fetch arbitrary URLs and return the markdown-converted contents.

    /mcp install fetch
Browse all 12 servers

Plus /mcp add for any custom server (npx, binary, or HTTP endpoint)

Skill marketplace

Skills that travel with you

Drop a SKILL.md in .codeep/skills/ and the agent auto-invokes it when triggers match. Publish to share — install on any machine with one command. Claude Code-compatible format.

  • update-dependenciesv1.0.0
    0

    Safely bump project dependencies for any detected ecosystem (npm/pnpm/yarn/bun, pip, cargo, go, SwiftPM): update within semver-safe ranges or a single named package, reinstall, then run build and tests to verify nothing broke — reverting or flagging on failure and summarizing what changed plus breaking notes.

    VladoIvankovicinstalls
    /skills install VladoIvankovic/update-dependencies
  • pr-reviewv1.0.0
    0

    Review the current uncommitted or branch diff before it ships: pull the diff with git, read changed files for context, and report correctness bugs, missing error handling, security issues, and test gaps grouped by severity, each with file:line and a concrete fix. Use before committing, opening a PR, or when asked to "review my changes / diff / branch." Read-only by default.

    VladoIvankovicinstalls
    /skills install VladoIvankovic/pr-review
  • swift-pkg-testv1.0.0
    0

    Build and test a Swift Package Manager package on macOS: run `swift build` then `swift test`, parse compiler and test failures, fix the source, and re-run until the build is clean and all tests pass. Use when asked to build/test/fix a Swift package, get a SwiftPM target green, or triage failing `swift test` output.

    VladoIvankovicinstalls
    /skills install VladoIvankovic/swift-pkg-test
Browse marketplace

Or write your first skill — Markdown + YAML frontmatter, ~5 minutes

Installation

Up and running
in 30 seconds

Choose your preferred install method. Codeep runs on macOS, Linux, and Windows (WSL). No configuration required — just run codeep to start.

✓
Node.js 20 or later
✓
Any terminal (zsh, bash, fish, PowerShell)
✓
API key for your preferred AI provider
# Install globally via npm
$ npm install -g codeep
 
# Then run
$ codeep

AI Providers

Use any LLM you want

Codeep works with all major AI providers. Switch between them at any time from the settings menu. Your keys are stored securely on your machine.

Anthropic

Claude — Fable, Opus, Sonnet and Haiku

Claude Opus 5Claude Fable 5.1Claude Fable 5

DeepSeek

Pro and Flash, both with a 1M context window

DeepSeek V4.1 Flash

Google AI

The Gemini line, from Pro down to the Flash-Lite tier

Gemini 3.1 ProGemini 3.8 FlashGemini 3.7 Flash

Grok (xAI)

Agentic coding and flagship models

Grok Build 0.1Grok 4.6Grok 4.5

Kimi (Moonshot)

Coding plan and pay-per-use

Kimi CodeKimi K3Kimi K3 (256K)

MiniMax

Coding plan and pay-per-use

MiniMax M3

Ollama (Local AI)

Run models locally or on a remote server — no API key required

Any installed modelLlamaQwen Coder

OpenAI

The GPT-5.6 ladder — Sol, Terra and Luna

GPT-5.6 SolGPT-6 AstraGPT-5.6 Terra

OpenRouter

One key, 100+ models from every major provider

100+ modelsopenrouter/auto

Qwen (Alibaba)

Coding Plan, Token Plan, pay-per-use, and live ModelScope catalog

Qwen3.7-PlusQwen3.6-PlusQwen3.5-Plus

Z.AI

Coding plan and pay-per-use

GLM-5.3GLM-5.3 FlashGLM-5.2

All providers use the OpenAI-compatible API format or Anthropic protocol. Switch anytime with /settings

Native app

Codeep for Mac

A first-class native desktop app — the same agent as the CLI, with a chat window, a project sidebar, inline diffs, and a real Settings pane. Built in SwiftUI, not an Electron wrapper.

  • Runs the full agent locally — shell, git, file edits
  • Project sidebar with inline diffs and tool confirmations
  • Every provider — Anthropic, OpenAI, Z.AI, Kimi, Qwen, Grok, MiniMax, Gemini, Ollama…
  • Keys in the iCloud Keychain; syncs with the CLI & dashboard
  • Auto-updates via Sparkle; Spotlight & Shortcuts built in
Get Codeep for Mac
New

Native Zed Editor integration

Codeep runs as a native AI agent inside Zed via the Agent Client Protocol (ACP). Use all 30+ Codeep commands directly from the Zed chat panel.

  • Full slash command support in Zed chat
  • Live tool call display as agent works
  • Thinking indicators during reasoning
  • File edit notifications in real-time
~/.config/zed/settings.json
// 1. Install Codeep
$ npm install -g codeep
 
// 2. Add to Zed settings
"agent_servers": {
"Codeep": {
"type": "custom",
"command": "codeep",
"args": ["acp"]
}
}
 
// 3. Open Zed AI panel → select Codeep → /help
New

VS Code extension

Codeep is now available as a VS Code extension. Get the full AI coding agent experience directly in your editor — no terminal required.

  • Chat sidebar with streaming responses
  • Live agent plan — watch multi-step tasks update in real time
  • Session browser — load and resume past conversations
  • Inline permission prompts with diff preview before Allow
  • Settings panel — switch model, provider, and mode
  • @file mentions — type @ to attach any workspace file
  • Send selected code or review any file from the editor
Install from Marketplace
VS Code
// Option 1 — install from terminal
$ code --install-extension VladoIvankovic.codeep
 
// Option 2 — search in Extensions panel
Cmd+Shift+X → search "Codeep"
 
// Open chat
Cmd+Shift+C or click the ⟨⟩ icon
 
// Requires Codeep CLI
$ npm install -g codeep

Releases

Shipping fast

RSSAll releases →

FAQ

Common questions

Don't see yours? Ask on the dashboard or start a discussion.

  • Is my code sent to a third party?
    Only to the LLM provider you choose, only when you invoke the agent. Codeep is a thin client over your API key — file contents, prompts, and tool calls go straight to Anthropic / OpenAI / Z.AI / OpenRouter / etc. We don't proxy anything through codeep.dev. The optional dashboard sync (opt-in via codeep account) uploads session metadata and learning preferences only — never raw code. Privacy details.
  • Does it work offline?
    Yes — pick ollama as your provider. Codeep talks to a local Ollama daemon, so no network call leaves your machine. Tool calls (read/write files, run commands) are unchanged. Smaller local models are slower at multi-step reasoning, so set /settings → Max Iterations higher and expect more back-and-forth. Provider docs.
  • What does it cost?
    Codeep is free to use — the CLI is open source (Apache 2.0), and the VS Code extension and GitHub Action are MIT. You pay your LLM provider directly. For OpenRouter, Codeep shows the exact usage.cost from each response on your dashboard. Prompt caching (default on Anthropic) typically reduces a session bill by 60-90%. For Z.AI on the GLM Coding Plan, it's flat-rate. How caching works.
  • Which model should I use?
    For coding: Claude Opus 5 (Anthropic) or GPT-5.6 are the strongest. For cost-per-token: DeepSeek V4 Pro or GLM-5.2 are 5-10× cheaper with little quality drop on typical tasks. For local: Llama 3.1 70B via Ollama (needs 24GB+ VRAM). Or set provider to openrouter and model openrouter/auto — the router picks for you per request. Provider matrix.
  • How does it compare to Cursor / Claude Code / Aider?
    Codeep is terminal-native (TUI + ACP for Zed / VS Code), multi-provider by design, and its CLI is open-source. Cursor is a fork of VS Code locked to its own backend. Claude Code is Anthropic-only and closed-source. Aider is terminal-native too but doesn't do ACP or skill bundles. If you want one tool that works the same across CLI, Zed, and VS Code with any provider — Codeep's the bet.
  • Can I use my own LLM endpoint?
    Yes — for any OpenAI-compatible endpoint, pick ollama provider and set /settings → Ollama URL to your endpoint. Authentication header is configurable. Self-hosted vLLM, LM Studio, or any inference server that speaks OpenAI's /v1/chat/completions works.
  • What's MCP and why should I care?
    Model Context Protocol — the emerging standard for letting LLMs talk to external systems. Codeep supports it end-to-end: connect a Postgres server, GitHub, browser automation, Slack, anything that speaks MCP. Browse 12 curated servers on the marketplace or add custom ones with /mcp add.
  • Do I need to log in to codeep.dev?
    No — Codeep works fully offline with just an LLM key. The optional account (free, GitHub OAuth) syncs session history, profiles, and learning preferences across machines, and unlocks the skill marketplace publish flow. Everything is opt-in. Account docs.

Start coding with AI today

Free to use. Works with your existing AI provider subscriptions. No account required to get started.

Read the docs
Star on GitHubFollow on XFollow on Bluesky