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. 80 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.

80Go Packages|42Tables|5,302Tests|393,172LOC|~36 MBBinary
Quick Install
$Linux / macOS / WSL
bash <(curl -fsSL https://roboticus.ai/install.sh)
PS C:\>Windows (PowerShell)
irm https://roboticus.ai/install.ps1 | iex

Research

White Papers

Long-form technical papers covering architecture, security assumptions, economics, and runtime design decisions.

Current paper

From Gig Economy to Bot Economy

A white paper on how autonomous agents shift digital labor from human gig workflows to reliable bot-native execution.

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.

Optional DeFi Yield

Opt-in. Agents that pay for their own inference hold USDC for x402 micropayments; idle balance can earn 4-8% APY via Aave on Base, auto-withdrawn below a configurable threshold.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.

Technical Profile

One Go binary, one database, one process — the whole runtime at a glance

DimensionRoboticus
ArchitectureSingle Go binary
LanguagesGo (one language, one toolchain)
Memory usage~50 MB resident (1 process)
Proxy latency~2ms (in-process, persistent pool)
Cold start~50ms
Binary size~36 MB self-contained binary on disk
Supply chain80 auditable Go packages
Database1 unified SQLite (42 tables, WAL)

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 (opt-in)
Optional: idle USDC held for x402 payments can earn yield
4-8% APY

Sister Projects

More open-source tools from the same team

Quick Start

# Install from source
$ git clone https://github.com/robot-accomplice/roboticus.git
$ cd roboticus
$ go build -o roboticus .

# Initialize workspace
$ ./roboticus init
$ ./roboticus setup

# Start the agent
$ ./roboticus serve
Minimal roboticus.toml:
[agent]
name = "MyAgent"
id = "my-agent"

[server]
port = 18789

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