agent6
A coding agent that jails every command and leaves your branch untouched. Each command the model runs goes through a sandbox, each step commits to the run's own hidden ref, and a verify gate certifies the tree before a run may finish.
Documentation: agent6.dev
the TUI the full agent, as a live dashboard |
the CLI the full agent, in any terminal |
the web UI the full agent, desktop or phone |
Install
uv tool install agent6 # or: pipx install agent6
agent6 connect # pick a provider, paste a key; or `connect chatgpt` / `connect claude` for a subscription
cd your-repo
agent6 run "add a --json output mode to the CLI"
Linux (x86_64/aarch64) with Python 3.12+; other platforms run without the sandbox behind a warning. Installation covers shell completion, PATH and building from source.
Why agent6
- Jailed commands. Every command the model asks to run goes through a jail that bounds what it reads, writes and reaches on the network;
autopicks the strongest level the host allows (Security). - Your branch stays yours. Each step commits to the run's own ref, so HEAD, the index and your branch are untouched until
sessions mergelands the work;resumecontinues a run andforkbranches it at any turn. - A verify gate. The repo's test command, inferred when unset, certifies the tree before a run may finish, and every surface shows the same green or red.
- One run, four front-ends. The CLI, the TUI, a browser on a desktop or phone, and an editor over ACP all drive the same runs;
attachfollows one live andsteerqueues an instruction from a script or a cron job. - State machines for long work.
.asm.tomlfiles you review, edit, run, watch and replay, with waits, operator input and steering built in (State machines). - Secure by default.
network = "auto",run_commands = "ask",protect_git = true; a fixed tool surface, eight runtime dependencies, no telemetry, no auto-update.
Providers: Anthropic, any OpenAI-compatible endpoint (OpenAI, OpenRouter, Ollama, vLLM, llama.cpp, LM Studio), a ChatGPT subscription, or the signed-in Claude Code binary, with model and reasoning effort set per role (Configuration).
Learn more
Usage walks through a first run, inspecting it and recovering one that went wrong; Architecture explains the loop, the task graph, compaction, memory and --parallel lanes.
1 maintainer
Metadata
1 maintainer
Release files for agent6 0.0.36
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| agent6-0.0.36.tar.gz | 1.4 MB | Details |
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent6-0.0.36-py3-none-manylinux_2_17_x86_64.musllinux_1_2_x86_64.whl | Python 3 | none | Linux musl 1.2+ x86-64, Linux glibc 2.17+ x86-64 | Details |
| agent6-0.0.36-py3-none-manylinux_2_17_aarch64.musllinux_1_2_aarch64.whl | Python 3 | none | Linux glibc 2.17+ ARM64, Linux musl 1.2+ ARM64 | Details |
Total release size: 5.1 MB
Release files / agent6-0.0.36.tar.gz
| Download URL | agent6-0.0.36.tar.gz |
|---|---|
| Size | 1.4 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d6a3d370066fd361fc9222360e83ab571c439ae04ec2698dad3f899d6fe69957
|
|
BLAKE2b-256 checksum How to use checksums |
5cd28e33f2ad2cae447173fc7a9f26e0fb882965a22ef180b5ad6e4be0d24a3a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 14, 2026.
Transparency logRelease files / agent6-0.0.36-py3-none-manylinux_2_17_x86_64.musllinux_1_2_x86_64.whl
| Download URL | agent6-0.0.36-py3-none-manylinux_2_17_x86_64.musllinux_1_2_x86_64.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Linux glibc 2.17+ x86-64 Linux musl 1.2+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
3c2806b0a1c65d3e9124aaa0dfdf394577d327f50c385b2ab62ec2a0dbf5c872
|
|
BLAKE2b-256 checksum How to use checksums |
205d72ea9b98732d077168ed7744438133744dbe1703aec3cba124b99afdda28
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 14, 2026.
Transparency logRelease files / agent6-0.0.36-py3-none-manylinux_2_17_aarch64.musllinux_1_2_aarch64.whl
| Download URL | agent6-0.0.36-py3-none-manylinux_2_17_aarch64.musllinux_1_2_aarch64.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Linux glibc 2.17+ ARM64 Linux musl 1.2+ ARM64 Python 3 |
|
SHA-256 checksum How to use checksums |
4565a5283ea8866a43976f4962ee56846a3c11a2ebee2969ca830a34aa1ecefd
|
|
BLAKE2b-256 checksum How to use checksums |
03bb545e4a03b63039301db825575479d9c9f99780a554b796009c27353f26e1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 14, 2026.
Transparency log
