Ten independent research-software objects connected through evidence, provenance, reproducibility, scientific communication, and longitudinal observation
Agentic Research Constellation is a project-level representation of ten independent research-software objects developed and maintained as a connected research system
Each software object retains its own repository, version history, scholarly identifier, archival lineage, technical scope, and research identity
The project does not collapse these objects into a single software package or analytical unit. Instead, it provides a shared organizational layer connecting work across agent systems, reproducible research infrastructure, evidence engineering, scientific communication, observatories, and persistent scholarly workflows
The constellation is organized around evidence, provenance, reproducibility, scientific communication, and longitudinal observation, while preserving the independent identity and history of every software object
Bilingual theory, evidence, and architecture-decision foundation for agent systems, with canonical sources, explicit claim states, implementation boundaries, validation states, and reproducibility discipline
Bilingual, source-grounded observatory tracing global AI from its intellectual and computational roots to the agentic frontier across models, protocols, runtimes, evaluation, safety, governance, and ecosystems
AST-driven research-document compiler for typed Markdown, structural-change evidence, diagnostics, artifact records and lineage, SARIF interchange, multi-format synchronization, and RO-Crate packaging
Dependency-free Python reference implementation for explicit data contracts, canonicalization, measurable state transitions, KL-divergence checks, validation, and reproducible repository boundaries
Bilingual, source-grounded observatory of China's AI and agent ecosystem across history, policy, standards, research, open source, infrastructure, industry, applications, evaluation, safety, and governance
Evidence-aware state-machine framework for research workflows with explicit claims, evidence, conflicts, runtime policy, checkpoints, provenance, claim verification, bounded transfer, and portable evidence handoff
Standard-library Python reference for versioned graph storage, SQLite persistence, FTS5 lexical retrieval, bounded graph analysis, entropy metrics, transactional ingestion, and evidence-aware reflection
Declarative scientific-figure compiler with explicit uncertainty semantics, accessibility intent, communication audits, provenance sidecars, portable figure evidence, and publisher-target boundaries
Public portal and research gateway for an edge-first AI research system spanning agent research, evidence engineering, research infrastructure, digital archaeology, and deterministic knowledge lifecycles
Standard-library research laboratory for deterministic state, evidence, reliability boundaries, agent action integrity, reproducible ledgers, and edge-native execution