The real catalog of tools for AI agents

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.

Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.

Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.

AI-engineering archive: search, what is new, forecasts, topic briefs, URL context; moderated inbox.

Verify a persona's DID-signed identity and query value-based judgment — advisory only, no actions.

Advisory context, intent, budget and API-ledger checks with free examples and x402 payments.

Verify whether a local Agent or MCP runtime matches an approved artifact.

Local MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.

MCP server for IBM Quantum computing services through Qiskit IBM Runtime

Model Context Protocol server for the Exogram Authority Runtime.

Zero-addon MCP server for Godot 4: agents edit, run, and play-test the game.

Local-first agent persona runtime (MCP): cross-session personality that survives compaction.

MCP runtime copilot for health checks, regressions, explainability, and operational memory.

Resumable API pagination, repeated-failure detection and tool-progress cache hints for AI agents

Self-hosted MCP server: 26 deterministic dev, security, and EVM tools.

In-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.

Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.

Architecture-aware MCP context with boundaries, seams, impact scope, and BGI-TWIN guidance.

Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.