the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

Agent skills for Gaia/LKM evidence-chain retrieval, evidence subgraph auditing, and scholarly review writing.

Tauri 2 desktop intelligence platform — Cesium.js 3D globe, 185 live panels, MCP server for Claude Code, and an explainable algorithm intelligence layer (truth scoring, evidence graph, compound risk, forecast calibration) plus shortage / weather / insights engines. 600+ deterministic tests.

A sourced web research agent on Cloudflare Workflows. Ask a question, follow evidence gaps, get a report with links.

Binary-Origami Figurator - evidence graph for investigative journalism with PROMPT scoring

Local-first evidence maps for AI agents working across unfamiliar codebases.

Map what your system proves: source-cited evidence graphs for security-control review

Open Employment Protocol — a reconciler, not a spec author. The candidate side and employer side each bring their own spec; OEP poses both arguments and settles a net outcome no single party owns. Built in the open, evidence-first. Protocol, not platform — the email of hiring.

Local-first Neo4j research entity graph for indexing concepts, claims, evidence, and cross-project relationships.

Quality Evidence Graph is a QA runtime that connects requirements, code changes, risks, test layers, evidence artifacts, and release gates into a reproducible graph for risk-based test placement and Go/No-Go decisions. - Quality Evidence Graph は、要求・コード差分・リスク・テストレイヤー・証跡 artifact・リリースゲートを単一のグラフに接続し、リスクベースのテスト配置と Go/No-Go 判断を再現可能にする QA Runtime です。

Drafting-core AI patent platform: robot evidence workflow for UCWS

Community-driven public-market research database for evidence, sources, observations, relationships, and investment theses.