An interactive terminal AI agent you can fully undo — any model, acts on your real files, every action reversible.
Project description
_ _
___ _ __ ___ _ __ __| | ___ | |_
/ _ \| '_ \ / _ \ '_ \ / _` |/ _ \| __|
| (_) | |_) | __/ | | | (_| | (_) | |_
\___/| .__/ \___|_| |_|\__,_|\___/ \__|
|_|
An interactive terminal AI agent you can fully undo.
opendot works directly on your real files and shell — but unlike other terminal
agents, every action it takes is snapshotted first, so you can see exactly
what it did and cleanly walk it back. Files and shell commands, not just
in-repo edits. Commands whose effects escape your workspace (network, sudo,
git push, deleting outside the working dir) are flagged and confirmed before
they run, with an honest note about what can't be undone.
That's the point of opendot: an agent you can let loose because nothing it does is a surprise, and (almost) nothing is irreversible.
Install
# try it instantly, no install
uvx opendot
# recommended (isolated global CLI)
uv tool install opendot # or: pipx install opendot
# also works
pip install opendot
Use
opendot # open an interactive chat
opendot -p "summarize this project" # one-shot, for scripts / CI
opendot --model claude-sonnet-4-5 # any model (see below)
opendot log # audit: what has the agent done here?
opendot undo # revert the last action
opendot undo 000004 # restore the workspace to before action #4
Inside the chat, slash-commands: /log, /undo, /clear, /compact,
/model, /help.
Any model
opendot uses LiteLLM, so any model works — cloud,
local, or Hugging Face. Set the provider's API key in your environment and pass
--model:
| Provider | Env var | Example --model |
|---|---|---|
| OpenAI | OPENAI_API_KEY |
gpt-4o |
| Anthropic | ANTHROPIC_API_KEY |
claude-sonnet-4-5 |
GEMINI_API_KEY |
gemini/gemini-2.0-flash |
|
| Ollama (local) | — | ollama/qwen2.5 |
Reasoning models stream their thinking live.
Connect MCP servers
opendot is an MCP client: connect any MCP server and its tools become available to the agent alongside the built-in ones.
# a stdio server — put its launch command after `--`
opendot mcp add <name> --env KEY=VALUE -- <command> [args...]
# a remote server (http/sse)
opendot mcp add <name> --url <https url>
opendot mcp list # show configured servers
opendot mcp remove <name> # remove one
Servers are stored in ~/.opendot/mcp.json and connect automatically on the
next launch; connected servers appear in the sidebar.
Because opendot can't know what an external tool does, every MCP tool call is treated as irreversible — it's confirmed before running and marked ✗ in the ledger. Your built-in file/shell actions stay snapshotted and undoable as usual.
Project rules — OPENDOT.md
Drop an OPENDOT.md in your project. Its prose is given to the agent as
context. You can also control what gets snapshotted with an opendot block:
```opendot
# snapshot these even though they'd normally be skipped:
snapshot: dist
# never snapshot these:
skip: data, *.log
```
By default opendot skips .git, node_modules, virtualenvs, and build caches
when snapshotting — your rules override those in either direction.
How the reversibility works
- Before every file write or shell command, opendot snapshots the working
directory into a content-addressed store in
~/.opendot(each unique file stored once, so snapshots are cheap). - Every action is recorded in an append-only ledger you can inspect with
opendot log. opendot undorestores the workspace to a chosen point, exactly.- A conservative classifier decides which shell commands are workspace- contained (auto-run, undoable) vs. escaping (confirmed first, marked irreversible). When unsure, it asks.
Honest boundary: opendot cannot undo effects that leave your machine (a sent
email, a dropped remote database, a git push). It tells you before running
those, rather than pretending otherwise.
Status
Early (alpha). The interactive agent, local tools, and the full reversibility
engine work and are tested. Streaming, slash-commands, and OPENDOT.md rules
are in. A richer TUI and more tools are coming.
MIT licensed.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file opendot-0.0.1.tar.gz.
File metadata
- Download URL: opendot-0.0.1.tar.gz
- Upload date:
- Size: 42.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4226bb03b59325294f4bd39a9aaa1d83e905855b112f2060d8947fe61282eccd
|
|
| MD5 |
0d3ed66232c8ae45ec046774272c898f
|
|
| BLAKE2b-256 |
689eb16c3da80bf45316f2f39f06226a6a2749c0a4369a1995ce98c987dcbcda
|
File details
Details for the file opendot-0.0.1-py3-none-any.whl.
File metadata
- Download URL: opendot-0.0.1-py3-none-any.whl
- Upload date:
- Size: 43.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
59b370a337bed315b1fd6f2136d067fe33d5968c52ea871ee37e2fb741215132
|
|
| MD5 |
1238a9b8337db7181f0ab202057399e5
|
|
| BLAKE2b-256 |
1d3f58319d85dd9ce51e82c4365d56774bda2dd5c7b438b4f11938ad2f419351
|