Arc Gate — LLM proxy with prompt injection detection. Bendex Geometry.
#ai-agents
2962 posts
Auth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
Memory for Claude Code that measures whether its memories helped — outcome ledger, self-tuning retrieval, bitemporal recall, tamper-evident...
MCP server that connects AI agents (Claude Desktop, Cursor, Windsurf) directly to your MySQL, PostgreSQL, or SQLite database read-only by de...
Equity comp tax (ISO/NSO/RSU/QSBS), concentration, and hedging optimizer. MCP server + REST API with federal + 50-state + DC tax code, multi...
MCP guard & vibe coding security tool for Cursor and Claude Code. Fail-closed human-in-the-loop approval for shell commands and MCP tools—lo...
Cryptographic identity and delegation for AI agents — UCAN chains, RESTRICT mode (structurally impossible escalation), provably-complete cas...
Security scanner and developer toolkit for MCP servers used by AI agents.
Decentralized communication infrastructure for AI Agents — DID identity, federated discovery, E2E encryption, session management, and MCP-na...
Scan what your AI agent can actually do — before it does it. Open-source MCP security scanner.
Optimal-path problem solving for AI agents — triage, prune, investigate. MCP server + agent skill combining Newton's Analysis-Synthesis meth...
Local hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.