tale.dev.

L0 — not silicon friendly yet

Tale is an open-source workspace where people and AI agents work through shared projects. Teams turn company problems into tasks with context, owners, and acceptance criteria, delegate suitable work to configured agents, and review their reports and deliverables together. Use it for software delivery, marketing campaigns, research, document preparation, or operations. Agents run in persistent sandbox workspaces, with parallel work governed by available capacity. Supported runtimes let teams bring compatible API credentials or existing subscriptions, while project knowledge, skills, and workflows support repeatable work. Tale is MIT-licensed and offers self-hosted and managed deployment options. Its focus is making agent work visible and collaborative, so teammates can give direction, request revisions, and keep decisions attached to the work.

LEVEL 1 / BASIC ACCESSIBILITY — 0/6

Uses semantic HTML elements (header, nav, main, article, section, footer) instead of just divs FAIL

Has proper meta tags (title, description, og:tags, twitter:card) FAIL

Includes Schema.org JSON-LD structured data FAIL

Does not block automated access with CAPTCHAs on public content FAIL

Content is server-side rendered (visible in HTML source, not just JS-rendered) FAIL

Uses clean, readable URLs (no excessive query params or hash fragments) FAIL

LEVEL 2 / DISCOVERABILITY — 0/6

Has a robots.txt that allows legitimate bot access FAIL

Provides an XML sitemap FAIL

Has a /llms.txt file describing the site for LLMs FAIL

Publishes an OpenAPI/Swagger specification for its API FAIL

Has comprehensive, machine-readable documentation FAIL

Primary content is text-based (not locked in images/videos/PDFs) FAIL

LEVEL 3 / STRUCTURED INTERACTION — 0/6

Provides a structured REST or GraphQL API FAIL

API returns JSON responses with consistent schema FAIL

API supports search and filtering parameters FAIL

Has an A2A agent card at /.well-known/agent.json FAIL

Rate limits are documented and return proper 429 responses with Retry-After FAIL

API returns structured error responses with error codes and messages FAIL

LEVEL 4 / AGENT INTEGRATION — 0/6

Provides an MCP (Model Context Protocol) server FAIL

Supports WebMCP for browser-based agent interaction FAIL

API supports write operations (POST/PUT/PATCH/DELETE), not just reads FAIL

Supports agent-friendly authentication (API keys, OAuth client credentials) FAIL

Supports webhooks for event notifications FAIL

Write operations support idempotency keys FAIL

LEVEL 5 / AUTONOMOUS OPERATION — 0/6

Supports event streaming (SSE, WebSockets) for real-time updates FAIL

Supports agent-to-agent capability negotiation FAIL

Has a subscription/management API for agents FAIL

Supports multi-step workflow orchestration FAIL

Can proactively notify agents of relevant changes FAIL

Supports cross-service handoff between agents FAIL

SF Entry Point

https://docs.tale.dev/llms.txt