OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Ankaloop

Ankaloop is a Python-based coding-agent runtime that reads, searches, edits, patches and executes code, with persistent sessions, memory, subagents, MCP and ACP connectivity, hooks and automation across CLI, server and Telegram interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ankaloop — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Ankaloop when a coding workflow needs a runnable agent rather than a framework assembled from separate components, especially when persistent context, code execution, subagents, MCP tools or CLI-to-Telegram access matter.

Who it is for

  • Developers working on software repositories
  • Teams building self-hosted coding-agent workflows
  • Users who need persistent project context and multiple agent interfaces
  • Developers integrating MCP-compatible tools into coding tasks

Documented uses

  • Inspect and search a repository
  • Create, edit and patch project files
  • Execute shell-based development tasks
  • Retain sessions, project rules and long-term memory
  • Delegate focused work to explorer, planner or coder subagents
Before you choose

Requirements & limits

The repository is public, declares an Apache-2.0 license, and documents installation through PyPI. The runtime requires Python 3.11 or newer and credentials for a supported model provider. Telegram support is an optional package extra.

  • Python 3.11+ is required.
  • A supported model provider and credentials are required for the documented quick start.
  • The same runtime serves CLI, HTTP/WebSocket and Telegram interfaces.
  • The tool loop includes file operations, shell execution, planning and subagent tasks.
  • Persistent sessions, project rules, memory and searchable history extend context across requests.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start Ankaloop in a project

Set up the Python package, configure a model provider and start the coding agent.

Before you start

  • Python 3.11 or newer
  • Credentials for a supported model provider

Steps

  1. Install the package with python -m pip install ankaloop.

  2. Run anka init to configure a provider.

  3. Run anka in the current project, or use anka --once for a single task.

Expected outcome

The Ankaloop coding-agent runtime starts in the selected project and can handle documented coding tasks.

Guide limitations

  • The documented setup requires provider credentials.
  • This recipe covers installation and startup, not a completed task result or deployment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
tao12345666333/ankaloop · Official homepage title · retained in its source language
How we review sourcesSuggest a correction