# Atlas changelog > Atlas is a model-agnostic, terminal-native AI coding agent. Plan, edit, and ship from the place you already live: your shell. The stable installer is currently serving **1.22.0**, released 2026-08-04. A version is listed here only once the stable installer actually serves it. A finished build is not a release you can download. ## Install ```sh curl -fsSL https://runatlas.sh/install | sh ``` Upgrade an existing install with `atlas upgrade`. Check what you are running with `atlas --version`. ## Releases ## 1.22.0 (2026-08-04) Atlas can now drive your command-line tools directly, with permissions scoped to the individual command rather than the whole binary. ### Per-verb permissions for your CLIs Until now, approving a command-line tool meant approving the tool. Atlas derived its permission pattern from the binary name, so allowing one Supabase command could allow every Supabase command, including the ones that drop a production database. Atlas 1.22 reads a manifest that classifies each verb on its own. Reads run without interrupting you. Writes ask. And a verb marked destructive asks every single time, with no setting anywhere that can turn that off. ```sh $ atlas toolchain PROVIDER VERSION VERBS LEARNED STATE gh 2.63.2 16 4 ready supabase 2.105.0 10 2 ready $ atlas toolchain doctor supabase supabase ready bin /usr/local/bin/supabase ok version 2.105.0, minimum 2.0.0 ok auth ok ok ``` - **New: Read-only commands stop interrupting you.** Listing pull requests, viewing a run, or reading a migration history is classified as a read and runs without a prompt. The interruptions move to the commands that can actually change something. - **New: Destructive commands cannot be silenced.** Dispatching a release, pushing a production schema, or deleting a repository asks every time. There is no always-allow for these and no configuration file that can grant one. - **New: Atlas tells you which tools are usable.** `atlas toolchain` lists every configured CLI with its version, whether it is authenticated, and whether it is ready. `atlas toolchain doctor` names the exact failure and the exact fix, and never tries to run an interactive login on your behalf. - **New: It stops re-learning the same mistake.** When a command fails and the next one succeeds, Atlas records what changed. The next session gets that lesson before its first call, so a flag you had to discover once does not have to be discovered again. - **New: Teach Atlas a new tool without writing code.** `atlas toolchain learn ` walks the tool's own help output and drafts a manifest for you to review. Against the GitHub CLI it classified 129 subcommands in one pass and flagged the ones it was unsure about. - **New: Credentials are stripped from tool output.** Tokens matching a provider's declared patterns are redacted before the output reaches the model, your transcript, or disk. - **Changed: Atlas prefers the tool over a raw shell command.** Running a configured CLI through the shell, or calling an API with curl when a tool already holds the credentials for it, is redirected to the tool path so the call gets classified. Pipelines still go to the shell. Set ATLAS_DISABLE_TOOLCHAIN_REDIRECT=1 to turn this off. - **New: Local model capabilities are read from Ollama.** Atlas asks Ollama what a local model actually supports instead of inferring it from the name. - **Fixed: The status line and permission prompt stay in the prompt dock.** - **Fixed: A published no-adaptive answer now beats the registry default.** Reviewed 2026-08-04. --- Canonical HTML: https://runatlas.sh/changelog Source of truth: src/content/changelog.ts (this file is generated from it, never hand-edited). Licence: Atlas is proprietary with a free core. It is not open source and there is no public source repository.