nanobot

nanobot is an ultra-lightweight, self-hosted personal AI agent framework in Python that runs in a browser WebUI, a terminal, or chat apps, combining tools, long-term memory, MCP and multi-agent delegation in a small core.

Agent frameworks

Visit website nanobot.wiki

It connects to Telegram, Discord, Slack, WeChat, email, Mattermost, Linear and other channels, and gives an agent tools such as files, shell access, web search, web fetch, MCP, cron scheduling, image generation and delegation to subagents, plus long-term memory through a feature called Dream. It can run long-horizon goals and scheduled automations on its own, and exposes both a Python SDK and an OpenAI-compatible API for embedding into other software.

A stable track installs from a released package and updates the same way, while an editable source-checkout track tracks the newest, less-tested changes; published packages include the WebUI, and supported-platform wheels also include a native TUI.

Requires Python 3.11 or newer. MIT licensed.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies