Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — While a thinking model works between steps, the agent screen now says it is waiting for the model and for how long, not "Listing" a tool that already finished. Auto-verify's checks show as…

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — Claude Sonnet 5.5 arrives (Opus 5.5 stays the default), Claude replies that start with thinking no longer come back empty, and a request Claude declines now says so instead of going quiet.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — A project can no longer replace one of your own MCP servers, a failed MCP server now says why, and /mcp browse drops the servers that are no longer maintained.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — OpenAI agent turns now use the Responses API: GPT-6 Astra is back with tool calls, GPT-6 Sol and Luna reason while they work, and GPT-6 Sol is the new OpenAI default.

TL;DR — Claude Opus 5.5 is the new Anthropic default, Grok 4.7 and GPT-6 Sol and Luna arrive, DeepSeek V4 Pro is back, and saved settings on retired models now move to their replacements.

TL;DR — Security release: a repository's own .git/config could make git run a program of its choosing, and opening the folder was enough. Codeep now neutralises those settings on every git call it…

TL;DR — Security and reliability release: a repo can no longer grant itself access or start MCP servers, secrets stay out of prompts, MCP tools ask first, and /commit, /scan, /undo and sessions stop…

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — Security release. A web page could redirect fetch_url into your own machine or network (localhost, cloud metadata, Tailscale), and the agent runs that tool without asking. Update now.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — DeepSeek cached tokens were billed at five times their price, and "saved via caching" was wrong for every provider not priced like Anthropic. Also a correction: 3.3.0 said Codeep could not…

TL;DR — /account answered "Unknown command", /stats has printed the /cost report since June, fresh installs started on an older model, and 40 commands were missing from /help. All fixed, and each is…

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — DeepSeek V4.1 Flash replaces both V4 models before DeepSeek routes V4 Pro to it on 14 September. Qwen 3.8 Max and Flash, GLM-5.3 in China, and four cost figures corrected — DeepSeek's by…

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — linking a server no longer means signing in to GitHub on it (it never did, nothing said so), and a device that failed to register once is no longer invisible and impossible to revoke.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free to use.

TL;DR — usage reports now include one boolean: whether the run was started from your phone. It exists to answer whether a Codeep iOS app is worth building with behaviour rather than a poll.

TL;DR — GPT-6 Astra and Gemini 3.8 Flash are in the model picker. Astra is not the default: it costs twice what GPT-5.6 Sol does and is still rolling out by organization.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

TL;DR — a long answer from a phone-started run now arrives whole, across up to three messages, instead of being cut at 3000 characters.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

Send Codeep an instruction from Telegram and it runs, with the answer coming back to the same chat — plus Claude Fable 5.1, a Sonnet 5 price that was 50% too high, and cache reads on Kimi and Qwen…

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

Codeep V3 is one release across three surfaces, so the three carry one number: the CLI moves 2.25.0 → 3.0.0, this extension 2.9.0 → 3.0.0, and the Mac app 1.14.0 → 3.0.0. Nothing here is a breaking…

Approval on your phone, on every platform — and the version numbers across the CLI, the Mac app and the VS Code extension now line up.

GLM-5.3-Flash: the same million-token window and tool calling as the flagship, at a twentieth of the price.

A rejected API key made an agent run look like it had simply run out of steps: every request was retried, the budget drained, and the report blamed the iteration limit.

Security rules had never once looked at a .mjs file, forEach + await only counted when it wasn't an arrow function, and the CI fix agent ran out of steps before it could finish.

Every run now records what it touched, including what the boundary refused — and four bugs that only a real session could surface.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

Agents you delete on the dashboard now disappear from your machines, sync says when it failed instead of going quiet, and a dependency advisory is closed.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

GLM-5.3 reached Z.AI's pay-per-use API and now carries the rate they publish, instead of no price at all.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

Custom bots land in the editor: pick one from the Agent Timeline toolbar, sync the set you built on the dashboard, and see exactly which capabilities each bot is allowed to use.

Custom bots you can actually trust: pin a model, grant only the capabilities you choose, and scope a bot to the projects it belongs to — enforced at runtime across CLI, Mac, VS Code and the dashboard.

Compatibility sync with CLI 2.15.0. No extension behaviour changes — the extension already speaks ACP to the CLI, so the CLI's new cross-tool features (AGENTS.md rules, .mcp.json, cross-device…

The last place /cost still priced plan usage: the prompt-caching savings line quoted dollars for subscription providers that bill a flat fee.

Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model, free & open source.

Subscription plans stop inventing dollar amounts — GLM Coding Plan, MiniMax, Kimi and Qwen now read "included in plan". Adds Grok 4.6, Gemini 3.7 Flash and GLM-5.3, and halves a Gemini rate stored…