HarperZ9

Local-first Project Telos MCP tool line for inspectable AI work: source intake, workspace context, routing ledgers, action receipts, and MATCH / DRIFT / UNVERIF

Local-first MCP tools for AI-assisted work receipts, workspace maps, routing ledgers, measured verdicts, and shared state verification across the five Project T

Offline repository and workspace maps, wikis, dependency graphs, and context artifacts with file:line provenance, zero runtime dependencies, and MCP.

Python and MCP tools for testing falsifiable claims and recording MATCH, DRIFT, or UNVERIFIABLE outcomes against supplied evidence.

Research intake that reaches the hard places: web, video, papers, scanned PDFs, browser, OCR, and audio into structured research packets. DOM extraction and cha

Coordinate agent fleets: routing, quality checks, prose contracts, and a replayable hash-chained ledger that preserves plans, evidence, results, and resumable h