Rust-Native Runtime.
Deterministic Autonomy.
Most AI agent frameworks are built with bloated Python libraries, leaking memory and generating unpredictable execution loops. Steffi takes a systems approach: a compiled Rust core managing local quantized routing engines, memory layers, and headless browser sessions natively.
Core Technology Pillars
Discover the low-latency, memory-safe primitives that allow Steffi agents to run 24/7 background tasks with high predictability.
Custom-Trained Local Brain (SLM)
Agents use a lightweight, specialized Small Language Model (SLM) running locally on the worker node. This model handles memory compaction and tool routing, selecting a maximum of 5 tools and 1 skill per message turn.
By shifting routing decisions to a local model, we eliminate high-latency remote calls and reduce API costs by up to 5x compared to standard agent platforms.
Specter Native Browser Engine
Built directly in Rust, the Specter browser enables agents to navigate single-page applications (SPAs) and execute web workflows natively and safely. Runs isolated without external browser processes.
Note: Specter skips WebGPU support to maintain lightweight execution, preventing complex WebGPU-based fingerprint or mining scripts from running.
Supervised DAG Scheduler
Task loops run as Directed Acyclic Graphs (DAGs) under strict process trees modeled after Erlang-OTP. If an agent thread gets stuck, the supervisor restarts it from its last memory hash.
Timezone-aware scheduling handles intervals, events, and cron rules with built-in missed-run recovery.
4-Tier Persistent Memory
Instead of simple history logs, Steffi utilizes a hybrid context engine. It saves episodic event paths, semantic domain guidelines, short-term context, and long-term key-value fact cards.
Vector database embeddings index the memory store, automatically loading the correct historical context in milliseconds without prompt bloating.
Engineered to Minimize Token Overhead
Standard Python-based frameworks pass entire chat histories and massive tool lists directly to external LLM APIs on every turn. This leads to prompt bloating, tool confusion, and soaring operational costs.
Architecture Comparison
| Feature Parameter | steffi.ai (Rust Engine) | Python Frameworks (LangChain/CrewAI) |
|---|---|---|
| Base Language | Compiled Rust (optimized binary) | Interpreted Python |
| Token Efficiency | Up to 5x fewer active tokens | Baseline (large full-history context) |
| Background Execution | Hours or days (fault-tolerant DAG) | Seconds or minutes (memory leak prone) |
| Memory Footprint | Sub-45MB base worker memory | 250MB - 1GB+ runtime dependency memory |
| Security Guardrails | Built-in 6-layer scanner binary | Basic regex filters (easily bypassed) |
| Package Sandboxing | Native Unix Socket gRPC docker gateway | Local shell execution (highly risky) |
The Rust Crate Structure
rb-core
Engine orchestrator, memory writers, and task execution registry.
rb-agent
Actor-model execution context, quantized LLM router, and council deliberation modes.
rb-plugin
SaaS connections, capability permissions, and MCP client implementations.
rb-guardrail
Prompt injection scanners, data loss prevention (DLP) masking, and text normalization.
rb-api
Dual-auth REST API endpoints and real-time WebSocket subscription channels.
rb-scheduler
Fault-tolerant cron scheduler and interval trigger handlers.
rb-storage
redb and PostgreSQL hybrid engine with active CDC synchronization.
rb-sdk-gateway
Per-run Unix Domain Socket (UDS) gRPC gateway for sandbox script environments.
The codebase internal prefix "rb" stands for "rusted-batata". In honor of sweet potatoes, the team developed batata-clean memory cycles to purge and compress vector caches dynamically!
Built by Olib AI
Steffi is engineered and maintained by Olib AI. Our team combines deep systems engineering, enterprise compliance, and AI research backgrounds.
Tyonna M.
CEOFormer Vice President of Operations at JP Morgan Chase. Tyonna directs corporate compliance, financial operations, and growth strategy.
Akram H. S.
Founder & CTOPreviously Lead Software Developer at Aloha. Akram oversees core development, Chromium engine compiler patches, and low-level modules.
Maya M.
Chief Architect of AIMaya directs on-device model deployment, llama.cpp fine-tuning, element matcher architectures, and semantic task processing.
Olib AI (founded 2024) is headquartered in Stone Mountain, Georgia, United States. Contact: support@olib.ai | sales@olib.ai