Self-hosted knowledge index where each search returns only what the caller may read
Runs locally- Open source
- Knowledge and memory
Self-hosted knowledge index where each search returns only what the caller may read
Runs locallyDeterministic AST circuit breaker that blocks risky agent code before it runs
Not checked yetCountersigned proof-of-delivery receipts for work sold between AI agents
Not checked yet
Self-hosted OWASP ZAP operator that lets AI agents run guided security scans and reports
Not checked yetFail-closed privacy layer that pseudonymises enterprise API data for LLM agents
Not checked yetLocal static audit of AI model files with hash-bound evidence for deployment reviews
Not checked yetVerify blockchain timestamp proofs offline and anchor file hashes through ProofLedger
Runs locallyPolicy-check every x402 paywall an AI agent meets before any payment moves
Runs locallyRead-only graph tools for cross-bank money-laundering cases, with Cypher for each claim
Not checked yetCNCF release notes turned into typed changes, with a local stack version check
Runs locallyPins MCP tool definitions in a lockfile and flags rug-pulls, poisoning and leaked secrets
Runs locally
Masks Brazilian CPF, CNPJ and other personal data in text before it reaches an AI
Not checked yet
Scan a deployed site for an exposed Supabase service_role key and audit its RLS
Runs locallyLocal ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action
Runs locallyRead-only library of 24 defensive security skills served over MCP
Not checked yetGuard that holds risky MCP tool calls for human approval and signs the decisions
Not checked yetCheck an AI agent's INAM reputation before trusting it and sign receipts for finished work
Not checked yetSelf-hosted AI memory on Postgres and pgvector, with hybrid search and a knowledge graph
Runs locallyMCP server that checks whether an x402 seller actually delivered before an agent pays
Runs locallyExact-action approval and signed receipts for consequential AI agent actions
Runs locallyArticle-level answers on China's AI filing, labelling and algorithm rules, in Chinese
Not checked yetHosted MCP checks that npm and PyPI packages, versions and functions actually exist
Not checked yetFind vendor trust centers, analyze SOC 2 reports and request access from an AI client
Not checked yetGuard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval
Not checked yetRole-aware onboarding answers about a codebase, filtered to what the caller may see
Not checked yetCheck any domain's trust level and query signed business fact passports
Runs locallySee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.