Project Info
Context
You do not search your workspace anymore. You text it.
Context is a native iOS AI teammate that lives in a messaging interface. It connects to your work tools, understands what changed, and replies like a concise coworker — not like a dashboard.
Why
Modern work is scattered across GitHub, Notion, calendars, Slack, and tickets. The common workflow is still manual: open five apps, scan updates, decide what matters, then act.
Context flips that interaction. You ask:
What should I work on first?
Context reads your workspace, reasons across sources, and responds with a prioritized answer plus tappable source cards.
What Works
- Native SwiftUI chat UI inspired by Apple Messages.
- FastAPI backend with streaming-compatible responses.
- Groq-powered LLM for fast development responses.
- Real GitHub reads for repo metadata, PRs, issues, commits, reviews, and checks.
- Notion page support for launch notes and project context, with demo fallback when unconfigured.
- Real Calendar ICS reads for today's events and meetings.
- Slack connector for team updates, with demo fallback when unconfigured.
- Workspace setup sheet for demo configuration without editing app code.
- Daily brief endpoint that summarizes GitHub, Notion, Calendar, and Slack context without a user prompt.
- Local conversation history so the chat survives app relaunches.
- Thinking states like "Searching GitHub," "Reading Notion," "Checking Calendar."
- Tappable source cards with native iOS preview sheets.
- Safe action drafts for GitHub issues, PR comments, and calendar events.
- Confirmed GitHub issue creation and PR comment posting through the backend.
- New Chat button to start fresh conversations.
Demo Flow
- Open the app.
- Context sends a morning brief.
- Ask:
What should I work on first? - Context checks GitHub, Notion, and Calendar.
- Context recommends the highest-priority work with sources.
- Tap a source card to inspect evidence.
- Tap
Draft issueto prepare an action. - Confirm creation only when ready.
Architecture
iOS SwiftUI app
├─ ChatView / ChatViewModel
├─ Source cards and action preview sheets
└─ APIClient
FastAPI backend
├─ /chat — streaming-compatible response stream
├─ /brief — daily workspace brief
├─ /connections — configured/demo source status
├─ /workspace/setup — runtime demo workspace configuration
├─ /actions/draft/github-issue
├─ /actions/draft/github-pr-comment
├─ /actions/draft/calendar-event
├─ /actions/create/github-issue
├─ /actions/create/github-pr-comment
├─ GitHub connector
├─ Calendar ICS connector
├─ Notion page connector
└─ Groq LLM provider
Tech Stack
- iOS: SwiftUI, async/await, MVVM
- Backend: Python, FastAPI, Pydantic
- AI: Groq for development LLM responses
- Workspace APIs: GitHub REST API, Notion API, iCal/ICS calendar feeds, Slack Web API
- Testing: pytest, httpx ASGI tests
How Codex And GPT-5.6 Were Used
Codex
Codex served as the primary engineering teammate throughout the hackathon build:
- Designed and iterated the SwiftUI chat architecture.
- Built the FastAPI backend and streaming-compatible chat contract.
- Implemented real GitHub, Notion, and Calendar connectors.
- Added a lightweight workspace setup flow for demo configuration.
- Created safe action endpoints for drafting and confirming GitHub issue creation and PR comments.
- Wrote backend tests for connectors, orchestration, and action flows.
- Debugged iOS-to-backend streaming and converted it into a stable demo flow.
- Shaped the product narrative, Devpost positioning, and demo story.
GPT-5.6
GPT-5.6 served as the planning and product reasoning partner:
- Refined the "AI teammate you text" concept.
- Prioritized MVP scope under hackathon constraints.
- Reviewed UX copy so Context sounds like a coworker, not a chatbot.
- Identified the strongest demo path: brief → prioritization → evidence → action.
Try The Chat Endpoint
The iOS demo currently points to the local FastAPI backend at http://127.0.0.1:8000.
curl -N -X POST http://127.0.0.1:8000/chat \
-H 'Content-Type: application/json' \
-d '{"message":"What should I work on first?"}'
Try The Daily Brief
curl http://127.0.0.1:8000/brief
Submission Materials
DEVPOST_SUBMISSION.md— copy-ready Devpost draft.DEMO.md— recording script and judge demo flow.SUBMISSION_CHECKLIST.md— final pre-submit checklist.
Analysis
View
Metric
- 3
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- FastAPIIn code
- PythonIn code
- SwiftIn code
3 of 3 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
244 KB
Source files
44
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
falafell99/context
55 files · 331 KB · @ 2039039
Structure
Interface
15 files · 27%Screens, components and styles rendered to the user.
Application logic
16 files · 29%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Swift52%
- Python33%
- Markdown14%
- YAML0%
- Shell0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
backend/requirements.txt
pypi · 9- fastapi
- groq
- httpx
- pydantic
- pydantic-settings
- pytest
- pytest-asyncio
- python-dotenv
- uvicorn[standard]
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.