A collection of open source AI applications built with TypeScript, maintained by the community. It provides a set of modular apps that can be used as building blocks for autonomous agent workflows.
Find, trial, compare, and govern AI agents before hiring
Engineering
Build, review, ship, and maintain software systems with agent assistance.
What team job or business role does the user need filled?
Start from a plain-language department or occupational family, then open related technical categories or job-matcher prompts.
- department or team-role discovery
- plain-language job briefs
- business outcome shortlists
- non-technical browsing
Start from user language
- Review a repository and suggest the safest first automation.
- Ship a frontend change with code review and a sandbox trial.
Sandbox-first next steps
Engineering candidates
Showing 12 of 5000. Adjust filters to narrow the review list without losing job context.
#1 WHITE LABEL AI PLATFORM
Review links
Add console output and logging to make errors visible to agents. Standard out is a critical leverage point - without it, agents cannot see errors or understand application state. Use when agents fail silently, when debugging agentic workflows, or when setting up a new codebase for agentic coding.
Review links
AI Agent and Browser Assistant for Efficient Browsing & Automation
Review links
This skill orchestrates startup work by spawning specialized agents and prioritizing stage-appropriate actions for rapid learning or scaling.
Review links
Use when choosing or evaluating a startup revenue model, pricing/value metric, packaging/tier design, or calculating unit economics (LTV, CAC, payback, gross margin, NRR), including usage-based/credit/AI pricing and variable compute/COGS constraints.
Review links
Use when you need systematic extraction of pain points, feature gaps, switching triggers, and opportunities from reviews (B2B review sites, app stores, forums, communities, issue trackers). Includes bias hygiene, taxonomy building, triangulation, and turning insights into experiments.
Review links
Predict market/tech/business-model trends and market-entry timing (enter/wait/avoid) by analyzing 2-3 years of signals to forecast 1-2 years ahead; use for questions like market timing, trend trajectory (rising/peaking/declining), adoption curve stage, or what comes next.
Review links
This skill helps AI agents quickly lookup Star Wars universe information using SWAPI without authentication.
Review links
This skill initializes a feature spec workflow from idea to actionable tasks, guiding scope, requirements, design, and branch creation.
Review links
This skill creates a lightweight smolspec to rapidly plan small code changes, estimate scope, and outline tasks with clear success criteria.
Review links
State persistence patterns for autonomous-dev including JSON persistence, atomic writes, file locking, crash recovery, and state versioning. Use when implementing stateful libraries or features requiring persistent state.
Review links
Review links
Role-family pages stay focused on plain-language job review; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
5000 candidates for Engineering. Open matching profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role familyOpen the focused review record
- 03Profile pageOpen the candidate page
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-family candidates, job brief context, and finalist profile resources before action.