4.5MB
Embedded Binary
SELF-GROWING AI AGENT INFRASTRUCTURE IN RUST
Production-grade AI agents that create their own tools, assemble into swarms, and get smarter with every run. 4.5 MB. 12-layer security. Pure Rust.
Say "summarize this video" — it decomposes the goal, creates missing tools, executes in parallel, and remembers what works. Next time, it's faster. Encrypted at rest, signed in transit, sandboxed at every layer. 🦀
4.5MB
Embedded Binary
8
Platform Targets
4
Client SDKs
58+
Built-in Tools
Create a tool on Monday, it's there on Friday. Define an agent once, it runs forever. Every capability you add is encrypted and persisted across sessions.
Describe a tool in plain English. The system creates it (shell, HTTP, LLM, or composite), registers it immediately, and persists it forever.
Say 'an agent that reviews my PRs daily' — name, system prompt, keywords, tools, and schedule are derived automatically.
Give a goal, get a parallel agent DAG. Each node gets only the tools it needs. Sandboxed execution with conflict detection.
4.5 MB embedded binary. Millisecond cold starts. Async Tokio runtime with streaming output.
Defense-in-depth: encrypted storage, path canonicalization, DNS rebinding protection, PII redaction, prompt injection detection, credential leak guards, and audit logging. Fail-closed from day one.
WASM plugins run in a bounded sandbox with fuel metering, memory caps, and Ed25519 signature verification required in production.
Telegram, Discord, Slack, and 20+ more. One agent, every platform. Add a channel with a single config line.
OpenAI, Anthropic, Google, Ollama, Candle local inference, and more. Swap providers with a config change — no code required.
Everything you need to run AI agents in production — nothing you don't.
Every tool you create and every agent you define persists encrypted. The system you use in month 2 has everything you built in month 1 — nothing is lost.
Describe a missing tool in conversation. The system creates it (shell, HTTP, LLM, composite), makes it available immediately, and persists it across sessions.
When a tool combo solves a task, it's saved as a recipe. Next time you ask something similar, those exact tools are selected automatically.
One static binary, zero runtime dependencies. 4.5 MB embedded, 18 MB full. Download and run.
No GC pauses, no null pointers, no data races. Compile-time guarantees eliminate entire classes of bugs.
12-layer defense-in-depth: XChaCha20-Poly1305 encryption, mTLS, HMAC request signing, PII/injection guardrails, credential leak detection, MCP binary attestation, and declarative YAML security policies.
OpenAI, Anthropic, Google, Ollama, Candle local inference, and 30+ more. Swap providers with a config change.
Linux (x86/ARM/musl), macOS (Intel/Apple Silicon), Windows. CI-tested on all three OS families.
Model Context Protocol for tool interop. Google A2A for agent-to-agent communication. Standards-first.
Give a goal in plain English. The system decomposes it into a parallel agent DAG, each node sandboxed with only the tools it needs.
Thin HTTP/WebSocket SDKs for Python, TypeScript, Swift, and Kotlin. Any platform that can make HTTP calls can control AgentZero.
Every gateway ships Scalar API docs at /docs. Explore and test all 40+ endpoints from the browser.
The most comprehensive security model in any AI agent framework.
Path canonicalization, symlink resolution, hard-link detection, sensitive file blocking (40+ patterns including .env.*, .kube/config, *.pem)
Context-aware quote parser, explicit command allowlist, backtick/dollar always blocked, output truncation
XChaCha20-Poly1305 AEAD with random nonces, 256-bit keys, file permissions 0o600, atomic writes
DNS rebinding protection, private IP blocking (RFC1918/link-local/carrier-grade NAT), constant-time token comparison
Pattern + Shannon entropy detection for 11+ secret formats, boundary isolation between local and remote channels, configurable patterns
PII redaction (email, phone, SSN, API keys) and prompt injection detection enabled by default in audit mode
Fuel metering, 256 MB memory cap, default-deny network/filesystem, Ed25519 signature required in release builds
mTLS client certificate verification, HMAC-SHA256 request signing with replay protection, TLS enforced in production mode
SHA-256 binary hash verification before spawning MCP server subprocesses
3-tier autonomy (ReadOnly/Supervised/Full), policy intersection for sub-agents, per-tool rate limits
YAML per-tool security policies with granular egress, filesystem, and command rules
Structured audit events, automatic secret redaction in errors/logs/panics, path sanitization in LLM-facing messages
One command. One binary. No dependencies.
$ curl -fsSL https://raw.githubusercontent.com/auser/agentzero/main/scripts/install.sh | bash
Or install with Cargo: cargo install agentzero
cargo install agentzero Single binary, no runtime dependencies.
agentzero onboard --interactive Interactive wizard writes agentzero.toml.
agentzero agent -m "hello" Send a message through the agent loop.
agentzero gateway HTTP/WebSocket gateway with chat, SSE streaming, and pairing.
4.5 MB, 12 security layers, 37+ LLM providers, 58+ tools. Agents that build themselves and never forget. Deploy it and walk away.