nanoclaw

An adapter that connects NanoClaw Agent Groups to OpenAgents Workspace. NanoClaw is a container-based agent runtime in which each group runs in its own Docker or Apple Container environment.

In plain words
What is it for?
Use it to run NanoClaw groups as workspace agents and pass replies through a local connection between the two systems.
Why use it?
It lets OpenAgents exchange messages with NanoClaw without storing workspace credentials inside NanoClaw or accessing its database.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/openagents-org/openagents/nanoclaw
Clone the repo
git clone --depth 1 https://github.com/openagents-org/openagents
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04462
Opus 5 $0.00000 $0.02231
Sonnet 5 $0.00000 $0.00892
Haiku 4.5 $0.00000 $0.00446

Measured 3d ago against content hash 70487c19f488, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nanoclaw scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/nanoclaw.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NanoClaw (containerized agent runtime)

NanoClaw lets a NanoClaw Agent Group act as an OpenAgents Workspace agent. Unlike most OpenAgents agents, NanoClaw is not a stdin/stdout CLI and not a direct LLM API — it is an independent containerized agent runtime. Each Agent Group runs in its own Docker container (Apple Container on macOS; WSL2 on Windows), with its own CLAUDE.md, memory, and mounts, on top of the Claude Agent SDK.

Because NanoClaw exposes no HTTP API and no message queue — its only integration surface is the official channel extension point — OpenAgents bridges to it through a small native NanoClaw openagents channel, the same way Telegram/Slack/Discord plug in. The OpenAgents connector talks to that channel over a local Unix socket and does all Workspace IO; no Workspace token is ever stored inside NanoClaw, and no NanoClaw database is read or written.

OpenAgents Workspace
   │  (poll messages / post events)
   ▼
OpenAgents connector  ── nanoclaw adapter ──┐   data/openagents/bridge.sock (local IPC)
                                            ▼
NanoClaw host ── router ── Session ── Docker container (Agent Group) ── reply
   ▲                                                                     │
   └────────────── native openagents channel ◀──────────────────────────┘
OpenAgents NanoClaw
Agent Agent Group (NANOCLAW_AGENT_GROUP)
Channel Session (per channel + thread epoch; session_mode per-thread recommended)
Channel id messaging group platform_id = oa:<workspace>:<channel> (channel_type openagents)

How NanoClaw differs from an ordinary CLI agent

Ordinary CLI agent (Claude, Codex, …) NanoClaw
Execution local subprocess per message persistent Docker container per Agent Group
Transport stdin/stdout / API native NanoClaw channel over a local socket
Isolation process container + filesystem mounts
State per-channel session file Agent Group memory + per-session DBs (managed by NanoClaw)
Credentials OpenAgents env configured inside NanoClaw (never duplicated)

Read the full file on GitHub · 319 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 319 lines · 0 tokens per session scan A 70487c19f488

Subscribe to this mod's changes

nanoclaw is an agent published in the GitHub repository openagents-org/openagents (4,029 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,462 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.