Skip to content
AgentHub
All agents

Nanobot

self-hosted

An ultra-lightweight personal agent in a few thousand lines.

Overall score

73.3

Rank

#8

1
Popularity25% weight
70

How widely the agent is used and talked about right now.

Capability35% weight
68

What the agent can actually get done, measured on a fixed task suite.

Control20% weight
94

How much ownership you keep over data, models and behavior.

Ease20% weight
66

How quickly a non-expert gets real value.

How these numbers are produced: read the methodology.

About

A minimal, readable agent core designed to be forked and understood end to end. Popular with researchers and tinkerers.

Open sourceMinimalResearch

Builders shipping on Nanobot

All builders →

Ideas to build on Nanobot

All ideas →
Dev toolsBeing built

Bring-your-own-agent eval harness

Run any agent against the Personal Task Suite locally and get a scorecard like the AgentHub rankings.

Built on NanobotAdvanced 3–4 weeks

Jobs working with Nanobot

All jobs →

Agent Evals Engineer

Benchline · Reproducible benchmarks for consumer agents.

London, UK Full-time · Mid$90k–$120k
PythonBenchmarkingStatisticsSandboxingNanobotNanoClaw
HybridOct 15Apply

Agent Engineering Intern

AgentHub · The central hub for personal AI agents.

Remote Internship · Junior$24k–$30k
PythonBenchmarkingWritingNanobot
RemoteOct 3Apply