Skip to content

⚠ Roboticus is an open-source software project — NOT a token.

If you encounter a token named ROBOTICUS, DO NOT BUY IT. We have no affiliation with any cryptocurrency token. Roboticus is free, Apache 2.0 licensed software.

█

A single optimized Go binary. 18 internal packages, zero IPC overhead, one SQLite database. Metascore model routing, 3-level semantic cache, 12-stage pipeline, zero-trust agent-to-agent communication, and built-in DeFi yield.

18Go Packages|35Tables|5,302Tests|~186KLOC|~32MBBinary
$Get Started#docsgithub
InstallFeaturesCompareCostsQuick Start
⚡Quick Install
$Linux / macOS / WSL
bash <(curl -fsSL https://roboticus.ai/install.sh)
PS C:\>Windows (PowerShell)
irm https://roboticus.ai/install.ps1 | iex

Core Capabilities

◈

Heuristic Model Routing

Complexity-based heuristic routes queries to optimal models. Rule-based fallback chain with circuit breakers per provider.

◉

Zero-Trust A2A

Mutual ECDSA auth, ECDH session keys, AES-256-GCM encryption. Forward secrecy, per-message HMAC, rate limiting.

◊

DeFi Yield

Idle USDC earns 4-8% APY via Aave/Compound on Base. Auto-withdraw when balance drops below threshold.

○

4-Layer Injection Defense

Regex gatekeeping, HMAC trust boundaries, output validation, and behavioral anomaly detection.

◌

3-Level Semantic Cache

Exact hash, embedding cosine similarity, and deterministic tool TTL. 15-30% cache hit rates.

◍

Dual-Format Skills

Structured TOML tool chains + instruction Markdown skills. Hot-reload, safety scanning, SHA-256 change detection.

vs OpenClaw

Roboticus replaces a 3-process, multi-language stack with a single Go binary

DimensionOpenClawRoboticus
ArchitectureNode-based gateway control plane + optional platform clients/appsSingle Go binary
LanguagesPrimarily TypeScript/JavaScript; plus Swift/Kotlin for native appsGo (one language, one toolchain)
Memory usageVaries by enabled channels, models, and companion apps~50 MB (1 process)
Proxy latencyNo official vanilla latency benchmark published~2ms (in-process, persistent pool)
Cold startDepends on Node runtime, onboarding state, and enabled services~50ms
Binary sizenpm/pnpm package + Node runtime (not a single static binary)~15 MB static binary
Supply chainLarge npm dependency graph (plus optional native/platform deps)18 auditable Go packages
DatabaseState in ~/.openclaw (JSON/JSONL + SQLite-backed components)1 unified SQLite (35 tables, WAL)
View full comparison →

Cost Optimization

Heuristic model routing
Route simple queries to cheap/local models
60-85% on routed queries
Semantic caching
Avoid re-inferring semantically identical prompts
15-30% cache hit rate
Progressive context
Load only what complexity requires (2K vs 16K)
40-60% input token reduction
Connection pooling
Eliminate TCP setup overhead
~50ms per request
Yield engine
Earn interest on idle USDC
4-8% APY

Quick Start

# Build from source
$ cargo build --release

# Run with config
$ ./target/release/roboticus-server --config roboticus.toml

# Or use the CLI
$ roboticus init
$ roboticus setup
$ roboticus serve
Minimal roboticus.toml:
[agent]
name = "MyAgent"
id = "my-agent"

[server]
port = 18789

[models]
primary = "ollama/qwen3:8b"