Skip to main content

Terminal agent for onchain analysis

Project description

English | 中文

KittyChain - Terminal agent for onchain analysis

KittyChain is a lightweight terminal AI agent focused on practical onchain investigation workflows. It combines a compact interactive CLI with built-in tools for wallet inspection, token analysis, web lookup, local file operations, and skill-based task guidance, so you can move from a question to an actionable chain analysis session in one place.

KittyChain home screenshot

Get Started

  1. Install KittyChain:
pip install kittychain
  1. Start the guided configuration flow:
kittychain --config
  1. Launch the interactive terminal UI:
kittychain

For coding work, start the coding-focused toolset:

kittychain --code

Features And Onchain Capabilities

  • Lightweight terminal agent loop with an interactive REPL and one-shot prompt mode.
  • Support for OpenAI-compatible and Anthropic-compatible model interfaces.
  • Built-in local tools for shell execution, file reading and editing, web search, web fetching with LLM summaries, TODO tracking, and skill loading.
  • Slash-command driven workflow for switching models, saving sessions, compacting context, and browsing loaded skills.
  • Session persistence and interruption support for longer investigative workflows.

KittyChain also includes built-in onchain analysis tools for common investigation tasks:

  • Address balance lookup
  • Address identity and label lookup
  • Address transfer inspection
  • Malicious address screening
  • Token info lookup
  • Token security checks

This makes KittyChain a practical fit for wallet triage, token due diligence, suspicious-address checks, and general blockchain research directly from the terminal.

Usage

Run the interactive terminal UI:

kittychain

Run the coding-focused mode:

kittychain --code

Run a one-shot prompt and exit:

kittychain -p "Check this wallet and summarize the risk signals"

Resume a saved session:

kittychain -r session_1234567890

Open the configuration wizard:

kittychain --config

You can also start KittyChain with the module entry point:

python -m kittychain

When the CLI is busy, press Esc to interrupt the current run at the next safe checkpoint.

Startup Modes

  • kittychain or kittychain --chain: load the default on-chain investigation toolset.
  • kittychain --code: load the coding-focused toolset for software engineering tasks.

Interactive Commands

Inside the REPL, KittyChain supports:

  • /help
  • /reset
  • /skills
  • /<skill name>
  • /model <name>
  • /tokens
  • /compact
  • /save
  • /sessions
  • /quit

The /skills command shows the skills loaded at startup. Slash commands also support prefix matching while typing, making it easier to discover available commands and skills from the terminal.

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

kittychain-1.0.1.tar.gz (1.5 MB view details)

Uploaded Source

Built Distribution

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

kittychain-1.0.1-py3-none-any.whl (1.1 MB view details)

Uploaded Python 3

File details

Details for the file kittychain-1.0.1.tar.gz.

File metadata

  • Download URL: kittychain-1.0.1.tar.gz
  • Upload date:
  • Size: 1.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for kittychain-1.0.1.tar.gz
Algorithm Hash digest
SHA256 caa161138b4fae28273c8640f638cf0537d28999407139a4d438dba3467f7f0c
MD5 6064e2cad197a28d1347ee1c3b5dfa40
BLAKE2b-256 18c05c922a46300c660339250680d41f06ef2a91403a6e4315636faf9493c323

See more details on using hashes here.

File details

Details for the file kittychain-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: kittychain-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 1.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for kittychain-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 cbcb84b16444c6357653c4c969ecd08b98350e3f754cf9e408317224af138e5e
MD5 d9f888beb5fecfbf81402cbbb26e422c
BLAKE2b-256 68f73a4e0ac8a1e6b700174dbba6468e21c4ba1ca4642278a71babc9459b5886

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page