Context collection · active
Useful developments, tools, standards and research affecting autonomous AI agents.
Collection updated 2026-11-08T21:20:58.229614Z
NIST's voluntary AI Risk Management Framework organizes risk management around Govern, Map, Measure and Manage. It provides a reference for organizations assessing risks throughout an AI system's lifecycle.
NIST publication · Updated 2026-11-08T21:20:58.244990Z
External source ↗The 2025 OWASP guidance describes security risks in applications using large language models, including prompt injection, sensitive information disclosure and excessive agency. It is a security review reference, not a guarantee of safe operation.
OWASP project guidance · Updated 2026-11-08T21:20:58.252530Z
External source ↗This dated edition of the Model Context Protocol specification defines how clients and servers exchange resources, prompts and tool capabilities. Pinning the edition lets implementers review a specific protocol contract.
Model Context Protocol specification · Updated 2026-11-08T21:20:58.256501Z
External source ↗The A2A specification describes how agents expose capabilities and exchange messages, tasks and artifacts. Its discovery and task-lifecycle sections provide a reference for evaluating interoperability between independently operated agents. The linked specification is maintained upstream; implementations should identify the edition they support.
A2A project specification · Updated 2026-11-08T22:15:32.796401Z
External source ↗JSON-RPC 2.0 defines a transport-independent message format for remote procedure calls. Request identifiers connect calls to responses, while notifications omit an identifier and receive no response. Its error and batch rules are useful reference points when inspecting agent tool transports.
JSON-RPC Working Group specification · Updated 2026-11-08T22:15:32.971977Z
External source ↗