agent7

The simplest coding agent. ~1500 lines of Python, four tools, one loop.

No orchestration: no plan mode, no subagents, no parallel tasks, no background jobs. You give it one sentence; it reads files, edits files, runs commands, then stops. Built for people who work on one thing at a time — you hold one task in your head, and so does it.

agent7/        1482 lines
  __main__.py   434   CLI + REPL + @path completion + session wiring
  agent.py      398   tools + agent loop + compaction
  commands.py   236   slash commands + model switching
  providers.py  161   API key auth
  store.py      149   atomic JSON session snapshots
  session.py    101   session state
  __init__.py     3   version

Install

pip install agent7
# or: uv tool install agent7
# or from source: uv sync && uv run agent7

Auth

Paste an API key; there is no OAuth. Keys are stored in ~/.config/agent7/auth.json.

export DEEPSEEK_API_KEY=sk-...
# export KIMI_API_KEY=...
# export MOONSHOT_API_KEY=sk-...
# export AGENT7_MODEL=deepseek-flash

You can also log in from inside the REPL:

/login deepseek
/login kimi              # optional: /login kimi global
/login moonshot
/model                   # list models for every logged-in provider
/model deepseek-flash

Usage

uv run agent7 "create hello.py that prints hi"   # one-shot
uv run agent7                                    # new REPL session
uv run agent7 -r                                 # resume latest session in this cwd
uv run agent7 -r <session-id>                    # resume a specific session
uv run agent7 session -l                         # list this cwd's sessions
uv run agent7 session "fix authentication"       # new named REPL session

Sessions are saved automatically after tasks, commands, interruptions, and exit. agent7 session -l prints tab-separated ID, NAME, and PATH columns and needs no login. Snapshots contain resumable model context, not a separate full transcript; compaction is reflected in the saved context. Files live in ${XDG_STATE_HOME:-~/.local/state}/agent7/sessions/ and do not store API keys. Hard process kills can lose the in-progress turn.

REPL commands: /help /model /status /login /logout /compact. Exit with an empty line or Ctrl-D.

Type @ in the REPL to recursively complete files and directories from the cwd: fix @agent7/agent.py. Tab accepts, directories keep going (@agent7/ → @agent7/session.py), and spaces are escaped (@my\ file.txt), so the path the model sees is the path it can read.

--cwd sets the working directory, --max-turns caps the loop (default 30 turns; when it runs out you get # (stopped after N turns)). A run that ends with no visible text never ends silently: you get either # (stopped after N turns), # no text in the reply … or # … hit the output token limit ….

Tools

That's it. No grep, no list_dir, no todo, no task. Need more capability? Let the agent use bash.

On startup agent7 picks a shell from sys.platform: Git Bash → PowerShell → cmd on Windows, bash elsewhere. The choice is written into the system prompt so the model matches the host. Override with AGENT7_SHELL=bash|powershell|cmd|/path/to/shell.

Tools run serially, one after another — so the log always reads in order and you never get three outputs interleaved. Edits are applied without a confirmation prompt; you just get a one-line diff stat.

Context

At 75% context usage, old tool/assistant text is compacted automatically: the last 3 user turns are kept, or for one-shot tasks the last 4 tool results. /compact triggers the same compaction manually.

AGENT7_CONTEXT_LIMIT overrides the context limit.

What it is not

• Not an orchestrator: no branching, no subagents
• Not a parallel framework: single-threaded, one thing at a time
• Not a background service: a foreground process, stopped with Ctrl-C
• No sandbox: tools run as you, and bash can do anything your account can do

If that kind of "small" is exactly what you want, this is enough. If it's missing the abstraction you had in mind, that omission is probably the point — not an oversight.