Progressive disclosure harnesses

Formats, runtimes, and patterns that reveal context, tools, or instructions in layers—index first, details on demand—to control tokens and improve agent focus (the "map, not encyclopedia" principle).

#	Project	Stars	Tier	OSS	Description
1	awesome-cursorrules ide	40k	super simple	✅	Curated .cursorrules and skills that leverage Cursor's index-then-load model; the canonical collection for rules-as-progressive-disclosure in the IDE.
2	agents.md typescript	22.4k	super simple	✅	Open format for repo-scoped agent briefings; v1.1 adds hierarchical scope and progressive disclosure so agents get a map of what exists, then load only what's relevant.
3	langgraph-bigtool tool-discoverypython	542	slightly complex	✅	Build LangGraph agents with large tool sets; retrieval and on-demand tool loading so agents scale beyond context without stuffing every schema upfront.
4	MCP-Zero tool-discovery	489	complex	✅	Active tool discovery for autonomous agents: model requests tools by requirement; hierarchical semantic routing over 308 servers / 2,797 tools with ~98% token reduction (APIBank).
5	ToolGen tool-discoverypython	180	complex	❓	ICLR 2025: unified tool retrieval and calling via generation; 47k+ tools without context stuffing—retrieval and invocation in one generative step.
6	spring-ai-tool-search-tool tool-discovery	74	mostly simple	✅	Dynamic tool discovery for Spring AI: model gets a search tool first, then pulls definitions for relevant tools; 34–64% token reduction across providers.
7	ToolRAG mcptool-discovery	28	mostly simple	✅	Semantic tool retrieval for LLMs; serves only the tools the user query demands (MCP-compatible), unlimited tool sets with zero context penalty.