Skip to main content

ramabana

rama's arrow

Agent runs a model against the tools supplied by a host. A host defines the folders, network access, memory, and approval gate available to the model. The terminal, MCP server, and Agent Client Protocol server use the same agent and tool contracts.

Start with one folder. Ramabana can write only inside the folders named by --root. Read access also stays inside those folders. --read-outside widens read access to the machine.

ramabana CLI on Gemma 4 LiteRT

Run it on a project

Install the terminal frontend and open the current folder:

pip install 'ramabana[cli]'
ramabana --root .

Omit the prompt for the interactive terminal. Pass a prompt for one turn that prints its answer and exits:

ramabana --root . 'Find where request timeouts are configured.'

Ramabana starts with --approve ask. Write tools wait for approval. --approve auto permits writes without asking for the rest of that process. --no-web removes the network tools.

Understand one turn

This example uses the same Agent.ask path as a real model. fake_agent supplies a deterministic backend and an in-memory project. The page runs without credentials, downloads, or writes to disk.

from ramabana.testing import fake_agent

agent, backend = fake_agent(replies=['The threshold is defined in `pkg/sizes.py`.'])
answer = agent.ask('Where is the threshold defined?')
answer
'The threshold is defined in `pkg/sizes.py`.'
assert answer == 'The threshold is defined in `pkg/sizes.py`.'
assert agent.history[-1]['prompt'] == 'Where is the threshold defined?'

agent.turn_lines(), repr(agent.turn_use)
(['🔍 Search Where is the threshold defined?'],
 '15 tok · in 10 · out 5 · model')

Choose a frontend

Use the terminal for an interactive coding session or a single shell command. Use MCP when another assistant needs Ramabana’s tools. MCP serves read-only tools by default. --write adds the write tools. Use ACP when an editor launches Ramabana as its agent.

ramabana --root .
ramabana-mcp --root .
ramabana-acp --root .

Add --model MODEL to pin the turn model. Add --vault to retain material read through the memory tools. Run each command with --help for its complete options.

Read the implementation

Start with the page for the contract you need:

Develop Ramabana

The notebooks are the source. nbdev-prepare generates the files under ramabana/.

uv sync --all-extras --group dev
uv run nbdev-prepare

nbdev-prepare exports the notebooks, runs notebook tests, cleans notebook metadata, and rebuilds the README.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ramabana-0.1.32.tar.gz (182.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ramabana-0.1.32-py3-none-any.whl (195.0 kB view details)

Uploaded Python 3

File details

Details for the file ramabana-0.1.32.tar.gz.

File metadata

  • Download URL: ramabana-0.1.32.tar.gz
  • Upload date:
  • Size: 182.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.1

File hashes

Hashes for ramabana-0.1.32.tar.gz
Algorithm Hash digest
SHA256 e4df8148f9ca2b36c4a3c4e0a5a65a5c96d0f20e493fbdcaf050a3fe5afa004a
MD5 9e5ad45f7fa5e0e03b8f7ec97515850c
BLAKE2b-256 a797f2b9b1676954765227ef298e1bcfce0b64758e3b759a396a4a467eb0283d

See more details on using hashes here.

File details

Details for the file ramabana-0.1.32-py3-none-any.whl.

File metadata

  • Download URL: ramabana-0.1.32-py3-none-any.whl
  • Upload date:
  • Size: 195.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.1

File hashes

Hashes for ramabana-0.1.32-py3-none-any.whl
Algorithm Hash digest
SHA256 4aba151ae416b62513d5e81952c5a25b733faa60768d29254197d9d4d9139d39
MD5 13995949c13c1ac3292c57986f57b7da
BLAKE2b-256 f8d36659e16dc470336f7dd48e58689092f4a8a8944b270f370f9b78c2cabea3

See more details on using hashes here.

Release history Release notifications | RSS feed

0.1.33

2 files

This release

0.1.32 This release

2 files

0.1.31

2 files

0.1.30

2 files

0.1.29

2 files

0.1.28

2 files

0.1.27

2 files

0.1.26

2 files

0.1.25

2 files

0.1.24

2 files

0.1.23

2 files

0.1.22

2 files

0.1.20

2 files

0.1.19

2 files

0.1.18

2 files

0.1.17

2 files

0.1.16

2 files

0.1.14

2 files

0.1.13

2 files

0.1.12

2 files

0.1.11

2 files

0.1.10

2 files

0.1.9

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.4

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page