Harrison Chase
S+Framework author / Agent Runtime / founder
This is the human-readable projection of the Digital Researcher's formal Watchlist. research/intelligence/REGISTRY.json remains the single source of truth; this page reads the Registry directly and does not maintain a second list.
People are the research subjects; repositories, papers, protocols, and official channels are the evidence and observation sources. Researcher counts and formal source-object counts are reported separately rather than added together.
Framework author / Agent Runtime / founder
Multi-agent framework author / researcher
Academic researcher / Multi-Agent / framework author
Multi-agent framework author / open-source founder
Agent memory / stateful runtime / founder
Agent memory / stateful runtime / research engineering
Protocol author / MCP core maintainer
Agent data / framework author / founder
Academic researcher / AI systems / framework author
Researcher / reasoning and agents
Academic researcher / benchmark and software agents
Academic researcher / realistic agent environments
Academic researcher / social agents / founder
AI safety and security researcher
Multi-agent framework author / founder
Agent ecosystem / developer relations / MCP
AI Engineer ecosystem / research media
Open-source maintainer / OpenHands
Agent engineer / OpenHands
Protocol / open-source maintainer / GitHub MCP
Agent / MCP engineering / GitHub
Open-source agent platform founder / OpenHands
Academic researcher / human-agent collaboration / verification
Academic researcher / social and safe agents
Agent researcher / OpenHands co-founder
AI research scientist / SWE-agent core author
Academic researcher / benchmark and autonomous systems
Protocol maintainer / agent infrastructure
Protocol / interaction-layer author / MCP Apps
Identity protocol expert / OAuth / MCP Auth
Data systems / AI evals / academic research
Engineering practitioner / AI evals / reliability
Academic researcher / agent reliability and auditability
Cursor / long-running and multi-agent runtime
OpenAI Agents SDK / runtime maintainer
OpenAI Codex / runtime collaborator
Cursor / agent autonomy and auto-review
Cursor / agent security and governance
Cursor / agent sandbox and MCP
Cursor / cloud agent runtime
Cursor founder / agent product and architecture
Runtime governance researcher
Multi-agent failure research
Multi-agent security researcher
Agent safety / skill-audit researcher
Agent failure-attribution researcher
Agent runtime policy researcher
ChatGPT, Codex, API and Agents product changes, documentation, enterprise controls and service status
Precision sections produce research leads only; reproduction or official corroboration is required for a platform fact.
Claude, Claude Code and API product changes, agent runtime and governance
Gemini, AI Studio, Vertex AI, Gemini CLI and ADK product and engineering changes
Precision sections produce research leads only; reproduction or official corroboration is required for a platform fact.
AI coding agents, Cloud Agents, CLI and developer workflow changes
Precision sections produce research leads only; reproduction or official corroboration is required for a platform fact.
Copilot Coding Agent, CLI, Code Review and GitHub-native agent capabilities
Precision sections produce research leads only; reproduction or official corroboration is required for a platform fact.
Microsoft 365 Copilot, Copilot Studio, Agent Builder and enterprise agent platform
Precision sections produce research leads only; reproduction or official corroboration is required for a platform fact.
Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employee · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employee · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architecture · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: digital-employee · open-source-engineeringVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · digital-employeeVisit GitHub ↗multi-agent-failure-taxonomy-and-traces
Serves: open-source-engineering · digital-employeeA taxonomy revision, new annotated trace release, benchmark or evaluator change, or reproducible result that can test TMPA evidence reconstruction or CodeFlowMu verification.
Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗Agent runtimes, protocols, SDKs, tools, recovery, evaluation, observability, and engineering changes.
Serves: open-source-engineering · industry-architectureVisit GitHub ↗auditable-agent-runtime
Serves: digital-employee · open-source-engineering · industry-architectureA new adapter, replay/rollback mechanism, or decision-record schema with reproducible evidence.
failure-attribution-benchmark
Serves: open-source-engineering · digital-employeeA new dataset, graph representation, localization result, or cross-corpus transfer result.
agent-audit-lifecycle-benchmark
Serves: open-source-engineering · digital-employeeThe paper is released, a board or dataset changes materially, an artifact limitation is resolved, or an independently reproducible result becomes relevant to TMPA evidence reconstruction or CodeFlowMu verification.
agent-work-practice
Serves: digital-employee · open-source-engineeringA reusable configuration-governance or multi-agent review mechanism relevant to FCoP or CodeFlowMu.
pre-deployment-agent-security
Serves: open-source-engineering · digital-employeeA release that adds a reproducible scanner, rule set, or risk model applicable to deployment gates.
runtime-policy-enforcement
Serves: digital-employee · open-source-engineering · industry-architectureA release that materially changes tool-call enforcement, approval, or audit-trail evidence.
agent-writing-quality
Serves: digital-employee · open-source-engineeringA rule or checker that can be compared with the JoinWell52 editorial scorecard.
research-publication-quality
Serves: open-source-engineering · digital-employeeA checklist change that can strengthen the TMPA publication gate without weakening evidence requirements.
anomaly-detection-method
Serves: open-source-engineeringA method or evaluation change directly applicable to Agent runtime anomaly signals.
anomaly-detection-research-index
Serves: open-source-engineering · digital-employeeA new cluster of resources that materially connects anomaly detection to Agent behavior or runtime governance.
runtime-path-policy
Serves: open-source-engineering · digital-employee · industry-architecturecovert-agent-communication
Serves: open-source-engineering · digital-employee · industry-architectureagent-skill-audit
Serves: open-source-engineering · digital-employee · industry-architectureagent-failure-attribution
Serves: open-source-engineering · digital-employee · industry-architectureagent-runtime-enforcement
Serves: open-source-engineering · digital-employee · industry-architectureAcademic preprints; focused on cs.MA, cs.SE and cs.AI
cs.MA · cs.SE · cs.AIVisit source ↗Autonomous Agents and Multi-Agent Systems; agent organization, coordination, protocols and governance
multi-agent systems · agent organization · coordination · protocol · governanceVisit source ↗Journal of Systems and Software; architecture, engineering, empirical evaluation and reproducibility
software architecture · software engineering · empirical evaluation · reproducibility · agent engineeringVisit source ↗Open research repository; software, datasets, artifacts and reproducibility evidence
multi-agent · agent runtime · orchestration · software artifact · reproducibilityVisit source ↗Open peer-review platform
conference-paper · reviewVisit source ↗Official OpenAI research
official-research · system-card · technical-reportVisit source ↗Official Anthropic research
official-research · system-card · technical-reportVisit source ↗Official Google DeepMind research
official-research · technical-reportVisit source ↗Microsoft Research; agents, enterprise AI, software engineering, systems and benchmarks
official-research · technical-report · benchmarkVisit source ↗ACL paper archive
conference-paper · journal-paperVisit source ↗Machine-learning proceedings
conference-paperVisit source ↗NeurIPS proceedings
conference-paperVisit source ↗ACM Digital Library
conference-paper · journal-paperVisit source ↗IEEE papers and standards
conference-paper · journal-paper · standardVisit source ↗A curated index of papers, datasets, benchmarks, standards, and tools for auditable AI. It is a discovery source; every useful entry must be verified against its primary source.
agent auditability · agent reliability · failure attribution · runtime monitoring · decision records · standards and governanceEvidence rule: Follow every useful entry to the original paper, official repository, dataset, benchmark, or standard before using it as evidence.