$ zeptoclaw agent --stream -m "Analyze our API for security issues"
🤖 ZeptoClaw — Streaming analysis...
[web_fetch] Fetching API docs...
[shell] Running integration tests...
[longterm_memory] Storing findings...
→ Found 12 endpoints, 3 missing auth headers, 1 open redirect
→ Saved findings to long-term memory under "api-audit"
✓ Analysis complete in 4.2s
We studied the best AI assistants — and their tradeoffs. OpenClaw's integrations without the 100MB. NanoClaw's security without the TypeScript bundle. PicoClaw's size without the bare-bones feature set. One Rust binary with 29 tools, 9 channels, 9 providers, and 6 sandbox runtimes.
Why ZeptoClaw
We studied what works — and what doesn't.
OpenClaw proved an AI assistant can handle 12 channels and 100+ skills. But it costs 100MB and 400K lines. NanoClaw proved security-first is possible. But it's still 50MB of TypeScript. PicoClaw proved AI assistants can run on $10 hardware. But it stripped out everything to get there.
ZeptoClaw took notes. The integrations, the security, the size discipline — without the tradeoffs each one made. One 6MB Rust binary that starts in 50ms, uses 6MB of RAM, and ships with container isolation, prompt injection detection, and a circuit breaker provider stack.
Security
AI agents execute code. Most frameworks trust that nothing will go wrong.
The OpenClaw ecosystem has seen CVE-2026-25253 (CVSS 8.8 — cross-site WebSocket hijacking to RCE), ClawHavoc (341 malicious skills, 9,000+ compromised installations), and 42,000 exposed instances with auth bypass. ZeptoClaw was built with this threat model in mind.
| Layer | What it does |
|---|---|
| 6 Sandbox Runtimes | Docker, Apple Container, Landlock, Firejail, Bubblewrap, or native — per request |
| Prompt Injection Detection | Aho-Corasick multi-pattern matcher (17 patterns) + 4 regex rules |
| Secret Leak Scanner | 22 regex patterns catch API keys, tokens, and credentials before they reach the LLM |
| Policy Engine | 7 rules blocking system file access, crypto key extraction, SQL injection, encoded exploits |
| Input Validator | 100KB limit, null byte detection, whitespace ratio analysis, repetition detection |
| Shell Blocklist | Regex patterns blocking reverse shells, rm -rf, privilege escalation |
| SSRF Prevention | DNS pinning, private IP blocking, IPv6 transition guard, scheme validation |
| Chain Alerting | Detects dangerous tool call sequences (write→execute, memory→execute) |
| Tool Approval Gate | Require explicit confirmation before executing dangerous tools |
Every layer runs by default. No flags to remember, no config to enable.
Install
# One-liner (macOS / Linux)
|
# Homebrew
# Docker
# Build from source
Quick Start
# Interactive setup (walks you through API keys, channels, workspace)
# Talk to your agent
# Stream responses token-by-token
# Use a built-in template
# Process prompts in batch
# Start as a Telegram/Slack/Discord/Webhook gateway
# With full container isolation per request
Migrate from OpenClaw
Already running OpenClaw? ZeptoClaw can import your config and skills in one command.
# Auto-detect OpenClaw installation (~/.openclaw, ~/.clawdbot, ~/.moldbot)
# Specify path manually
# Preview what would be migrated (no files written)
# Non-interactive (skip confirmation prompts)
The migration command:
- Converts provider API keys, model settings, and channel configs
- Copies skills to
~/.zeptoclaw/skills/ - Backs up your existing ZeptoClaw config before overwriting
- Validates the migrated config and reports any issues
- Lists features that can't be automatically ported
Supports JSON and JSON5 config files (comments, trailing commas, unquoted keys).
Deploy
Any VPS
|
Installs the binary and prints next steps. Run zeptoclaw onboard to configure providers and channels.
Providers
ZeptoClaw supports 9 LLM providers. All OpenAI-compatible endpoints work out of the box.
| Provider | Config key | Setup |
|---|---|---|
| Anthropic | anthropic |
api_key |
| OpenAI | openai |
api_key |
| OpenRouter | openrouter |
api_key |
| Groq | groq |
api_key |
| Ollama | ollama |
api_key (any value) |
| VLLM | vllm |
api_key (any value) |
| Google Gemini | gemini |
api_key |
| NVIDIA NIM | nvidia |
api_key |
| Zhipu (GLM) | zhipu |
api_key |
Configure in ~/.zeptoclaw/config.json or via environment variables:
Any provider's base URL can be overridden with api_base for proxies or self-hosted endpoints. See the provider docs for full details.
Features
Core
| Feature | What it does |
|---|---|
| Multi-Provider LLM | 9 providers with SSE streaming, retry with backoff + budget cap, auto-failover |
| 29 Tools + Plugins | Shell, filesystem, web, git, stripe, PDF, transcription, Android ADB, and more |
| Tool Composition | Create new tools from natural language descriptions — composable {{param}} templates |
| Agent Swarms | Delegate to sub-agents with parallel fan-out, aggregation, and cost-aware routing |
| Library Facade | Embed as a crate — ZeptoAgent::builder().provider(p).tool(t).build() for Tauri/GUI apps |
| Batch Mode | Process hundreds of prompts from text/JSONL files with template support |
| Agent Modes | Observer, Assistant, Autonomous — category-based tool access control |
Channels & Integration
| Feature | What it does |
|---|---|
| 9-Channel Gateway | Telegram, Slack, Discord, WhatsApp (bridge + Cloud), Lark, Email, Webhook, Serial — unified message bus |
| Persona System | Per-chat personality switching via /persona command with LTM persistence |
| Plugin System | JSON manifest plugins auto-discovered from ~/.zeptoclaw/plugins/ |
| Hooks | before_tool, after_tool, on_error with Log, Block, and Notify actions |
| Cron & Heartbeat | Schedule recurring tasks, proactive check-ins, background spawning |
| Memory & History | Workspace memory, long-term key-value store, conversation history |
Security & Ops
| Feature | What it does |
|---|---|
| 6 Sandbox Runtimes | Docker, Apple Container, Landlock, Firejail, Bubblewrap, or native |
| Gateway Startup Guard | Degrade gracefully after N crashes — prevents crash loops |
| Channel Supervisor | Auto-restart dead channels with cooldown and max-restart limits |
| Tool Approval Gate | Policy-based gating — require confirmation for dangerous tools |
| SSRF Prevention | DNS pinning, private IP blocking, IPv6 transition guard, scheme validation |
| Shell Blocklist | Regex patterns blocking reverse shells, rm -rf, privilege escalation |
| Token Budget & Cost | Per-session budget enforcement, per-model cost estimation for 8 models |
| Rich Health Endpoint | /health with version, uptime, RSS, usage metrics, component checks |
| Telemetry | Prometheus + JSON metrics export, structured logging, per-tenant tracing |
| Self-Update | zeptoclaw update downloads latest release from GitHub |
| Loop Guard | SHA256 tool-call repetition detection with circuit-breaker stop |
| Context Trimming | Normal/emergency/critical compaction tiers (70%/90%/95%) for context window management |
| Session Repair | Auto-fixes orphan tool results, empty/duplicate messages, and alternation issues |
| Config Hot-Reload | Gateway polls config mtime every 30s and applies provider/channel/safety updates live |
| Hands-Lite | HAND.toml agent profiles with bundled presets (researcher, coder, monitor) and hand CLI |
| Multi-Tenant | Hundreds of tenants on one VPS — isolated workspaces, ~6MB RAM each |
Full documentation — zeptoclaw.com/docs covers configuration, environment variables, CLI reference, deployment guides, and more.
Inspired By
ZeptoClaw is inspired by projects in the open-source AI agent ecosystem — OpenClaw, NanoClaw, and PicoClaw — each taking a different approach to the same problem. ZeptoClaw's contribution is Rust's memory safety, async performance, and container isolation for production multi-tenant deployments.
Usage
# CLI agent (one-shot)
# Streaming output
# Use a template (researcher, coder, task-manager, etc.)
# Batch process prompts from a file
# Run as a multi-channel gateway (Telegram, Slack, Discord, etc.)
# With container isolation per request
# Manage long-term memory
# Self-update to latest release
# Encrypt secrets in config
# Manage agent hands (profiles)
Development
# Build
# Run all tests (~2,900 total)
# Lint and format (required before every PR)
See CLAUDE.md for full architecture reference, AGENTS.md for coding guidelines, and docs/ for benchmarks, multi-tenant deployment, and performance guides.
Contributing
We welcome contributions! Please read CONTRIBUTING.md for:
- How to set up your fork and branch from upstream
- Issue-first workflow (open an issue before coding)
- Pull request process and quality gates
- Guides for adding new tools, channels, and providers
License
Apache 2.0 — see LICENSE
Disclaimer
ZeptoClaw is a pure open-source software project. It has no token, no cryptocurrency, no blockchain component, and no financial instrument of any kind. This project is not affiliated with any token or financial product.