Le catalogue réel des outils pour IA

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Constitutional AI kernel with 13 MCP tools, 888_JUDGE verdict pipeline, and VAULT999 ledger.

Verify consequential AI actions before they execute.

Deterministic research state, evidence validation and statistical recomputation.

Unofficial safety-focused MCP server for Kalshi market data and explicitly authorized trading

Access Kernel's cloud-based browsers and app actions via MCP (remote HTTP + OAuth).

Run a side effect exactly once under retries, redelivery, and concurrent workers.

Agent-first CAD: editable .kcad.ts source, deterministic review, OpenCASCADE kernel.

Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.

Linux kernel CVE analyzer: upload a .config, get a CycloneDX VEX report of affecting CVEs.

Free dual MCP+agent registry. Probe Live, free demo, Kernel/Loop. Self-list + dual strategy.

Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).

Persistent semantic memory storage, associative recall, and recent memory index by namespace.

Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.

Persistent business-intelligence memory for AI agents.

An MCP memory server. One memory your agents share — across models, devices and apps.

Cross-session memory for AI agents with a Source Receipt for every memory, over MCP.

Private cross-media memory for AI assistants: recommendations, progress and controlled actions.

One user-owned memory shared across AI assistants: recall, spaces, and confirmed references.

Company memory for your team and its AI agents. Hosted service, account required.