Find the tests you can delete. Per-test line coverage for Jest, weighted by line rarity, plus mutation testing and test quality scoring.

Abstract durable session persistence seam (ctx.sessionPersistence) for the DeepSeek Harness

Shared in-process subagent run driver: drives a child agent on ctx.agents (used by the spawn and fork backends)

Agent interface, registry, initiator scope, and event vocabulary for the xneog

Model-facing fresh-agent Ralph loop over the workflow and subagent seams

Trajectory event ledger with an interactive timing overview: pure-consumer plugin registering into the conversation ViewMap (no service)

Git-native causal history runtime for intent writes, timeline reads, and receipts.

Provider-neutral peer state and effect contracts for AgentPlat Mesh applications.

LLM and code evaluators for Fabric Experiments: judge library, ModelClient contract, run aggregation.

Algorithmic conversation compactor for pi - transcript-preserving structured summaries, no LLM calls

Proof-of-Time attestation — Ed25519-signed timestamps with multi-source corroboration and explicit error bounds. IETF draft-helmprotocol-tttps

Model-facing same-session goal tools with execution-time authority checks

OpenMetadata MCP server - metadata management, lineage, search, data quality, and more

Agent interface, registry, initiator scope, and event vocabulary for the agentBrain Harness

Deterministic evidence contracts for dataset lineage, bounded influence, revisable identity evidence, and non-economic attribution

On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.

Trace rendered React elements back to API response fields

Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness

Systems-testing and runtime-validation tooling for the causal-order stack.

Platform-agnostic Klyfa analytics core (transport, queue, consent, flags, exposures) shared by @klyfa/react-native and @klyfa/web.