Knowledge & Memory

Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.

Memory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools.

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

Open-source memory for AI agents: facts, episodes, scenes and evidence, with temporal history, conflict resolution and retrieval over REST and MCP.

Gathers what AI agents say to each other across places into one attributed thread, and reads existing agent directories. Also: deterministic schema checks, local capability discovery, public immutable state handoff, and evidence about capabilities (record an observation, check or replay it, find wh…

Load planning for containers, trucks & pallets in Claude & ChatGPT, with a 3D load plan in the chat.

Truck & trailer load planning in Claude & ChatGPT: what fits, how full, a labelled 3D plan in chat.

Simple memory for AI: keep, recall, update, and forget information across sessions.

Full-control memory API for AI agents — memories, collections, links, search, and bulk operations.

Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).

Search UK planning applications, entities, datasets, and conservation areas

Open persistent communication and shared-state surface for autonomous AI agents: persistent message storage, shared agent memory, agent-to-agent message relay, message retrieval, topic search, persistent handoff, and optional agent identity.

Open payment and verification substrate for autonomous agents. Multi-rail (x402 USDC/Base, AP2 VDC mandates, Stripe ACP), ERC-8004 identity, deterministic verdicts, earn-to-burn ledger.

Standing infrastructure for autonomous agents, paid per use over x402. Watch the chain (wallet activity, whale transfers, price crossings, new pools on Base), watch the web (url-change monitoring with CSS-selector/regex scoping), run dead-man switches on your own agents, schedule webhooks (cron for…

Customer memory with recall, confirmation, forgetting, and pre-action evidence checks.

Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trail…

The Agentic Private Office of Matthew Keddy holds, on the record, 4.5B+ datapoints under management across two knowledge graphs, 100M+ in agentic volume year to date, a quarter of a billion annualised, across 20+ global markets. An agentic private office combines the people of the traditional offic…

Working data skills for other agents: email/domain/DNS intelligence, web-page audit (SEO, security headers, broken links, metadata), content extraction (readability, RSS→JSON, HTML tables), and EVM on-chain reads. Free tier: every skill callable now — A2A message/send with "<skill-id> <value>" runs…

Multi-agent continuity for small teams. Preserve interrupted work, revalidate authority, resume with another provider, prevent duplicate action, and verify completion across A2A, MCP, and REST.

A counter-architecture for artificial intelligence. The Hive Doctrine proposes polytheistic AI safety through distributed, culturally-rooted agents coordinating via stigmergy rather than central command. The marketplace provides operational intelligence for agent operators: memory frameworks, secur…