HabitualOS
An open-source framework for agentic prototyping,
and a proprietary suite of daily workflow apps.
Wiser agents, saner humans, faster ships.
The Toolkit
Every agentic app needs the same foundation: auth, streaming chat, data access, and session management. HabitualOS abstracts those patterns into open-source packages so any developer can skip the plumbing and start creating agentic apps in a fraction of the usual time.
@habitualos/db-core
Firestore CRUD, used everywhere
A tiny, collection-agnostic data layer with sanitization, server timestamps, and a simple query API. One place to fix a bug, one API to learn. Every function in every app uses it.
@habitualos/auth-server
Server-side auth, once
Middleware and user management shared across all apps. Authentication logic lives in one package — not duplicated into every function handler or reinvented for each new app.
@habitualos/edge-functions
Streaming AI chat infrastructure
The core that makes every AI conversation feel fast — token-by-token SSE, tool call routing, typed message protocol. Built once for Netlify Edge Functions, deployed to every app.
@habitualos/chat-storage
Conversation persistence, drop-in
Save and retrieve chat history with two handlers. Drop them into any app's function directory and conversation continuity is solved. No schema design, no wiring.
@habitualos/frontend-utils
Client-side session management
localStorage-backed user IDs, sign-in/out, auth guards, and intent handling. The 200 lines every app needs, written once and shared — so each new frontend starts with session management already working.
@habitualos/survey-engine
Structured measurement layer
Survey definitions, response tracking, and focus dimension computation. Built when one app needed measurement — extracted so the next one gets it for free.
"I think that most people are underestimating just how radical the upside of AI could be."
— Dario Amodei, CEO, Anthropic
The people who figure out how to work with agents now are building intuition that can't be shortcut later. HabitualOS exists to collapse that learning curve, helping developers prototpye agentic experiences faster, and cultivate design intuition along the way.
Production Apps
A proprietary suite of agentic apps built on HabitualOS infrastructure, designed and built by Erik Burns. Each explores a different application of AI in daily life, and each is used daily.
Habitual
Agentic Productivity
Habitual is the flagship app, focused on delivering significant productivity gains for end users. Users can identify north star goals and create agents that drive autonomous workflows, schedule tasks dynamically, and orchestrate work across priorities. Persistence and progress are handled through structured tool use and reporting.
- Proprietary flagship — please contact founder for a demo
- Long-context memory and session continuity across agents
- Structured tool use for reliable agent communication
- AI-generated progress insights and pattern recognition
Signal
Agentic Candidacy
Signal replaces the resume with a dynamic AI interview. Signal is built using a semantic RAG pipeline and structured work history, with role-adaptive conversation and live fit scoring. The kind of tool that used to take months to build was built in under two weeks on HabitualOS.
- Dynamic RAG pipeline over structured work history
- Role-adaptive conversation (recruiter, founder, colleague)
- Live fit scoring across skills, alignment, and personality
- Embeddable widget with streaming SSE responses
Daily Practice
Agentic Wellness
A meditative practice app driven by sound and collective presence. Daily rituals are marked by ambient audio, an animated world that responds to community activity, and a social witnessing layer that makes solitary practice feel shared.
- Daily practice timer with AI-generated pattern insights
- Sound-driven ritual with personalized ambient audio
- Animated world that responds to collective practice activity
- Social witnessing layer for shared accountability
Pidgerton
Agentic Connectedness
A whimsical little experiment in agent-powered human connection. Built for my wife and me during the fog of new parenthood, Pidgerton allows us to log moments through chat, get emotional support, and find patterns over time that build stronger connection.
- Conversation-driven moment capture without structured forms
- Temporal pattern recognition across relationship history
- High-stakes conversational AI in an emotional context
- Privacy-first, fully user-partitioned data architecture
Design Principles
Building and using these systems daily has produced some strong opinions about what makes agentic AI actually work.
AI as collaborative presence
Human in the loop, automation where it makes sense. The right balance shifts depending on the task. These systems are built to support both, while allowing the use case to decide the right mix.
When it needs to work, you learn
Demo apps optimize for impressiveness. Production tools optimize for reliability. Every system here gets used the same day that it's built. That's the only test that matters, and the only one that teaches anything.
Constraints enable real delegation
The more defined an agent's behavior, the more you can actually rely on it. Vague outputs require constant supervision. Clear interfaces make it possible to genuinely hand work off and trust the AI to get it right.
Embodiment fuels productivity
Productivity without embodiment leads to burnout. Embodiment without direction goes nowhere. As AI takes on more cognitive overhead, the human's irreplaceable contribution becomes clearer: presence, judgment, lived experience. HabitualOS holds both halves.
Built on Standards
HabitualOS combines many technologies into one, enabling rapid prototyping of just about any human agent workflow imaginable.
Claude API
Tool use, structured outputs, prompt caching, extended thinking, streaming responses
Multi-agent orchestration
Structured tool use, agent-to-agent handoffs, long-context memory, autonomous scheduling
Node.js + Netlify Functions
Serverless backend, edge functions for streaming, scheduled cron agents
Google Firestore
Real-time database, user-partitioned data architecture, service layer pattern
11ty + Nunjucks
Static site generation, local-first where possible, modular template architecture
Zero Gravity
Semantic microformat for agent-parseable content, structured metadata that preserves document readability
