agentralabs

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.

Structured agent-to-agent and agent-to-human communication — channels, pub/sub, message routing, and presence. One .acomm file. Rust core + MCP server.

Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.

Shared contracts for the Agentra ecosystem — traits, types, and standards that all sisters implement

Temporal reasoning for AI agents — deadlines, schedules, sequences, duration estimation (PERT), and decay models. One .atime file. Rust core + MCP server.

Cryptographic agent identity with Ed25519 anchors, signed action receipts, and scoped trust delegation. One .aid file. Any agent. Any LLM.

Intent compilation and uncertainty detection for AI agents — truth verification, ambiguity resolution, causal reasoning. Rust core + MCP server.

Streaming validation engine for AI agents — real-time code validation during generation, shadow execution, protection layers. Rust core + MCP server.

Blueprint engine for complete project architecture before code generation — entity inference, dependency resolution, skeleton generation. Rust core + MCP server.

Pattern library engine for AI agents — crystallizes verified code patterns for instant rebuilds, 15-second subsequent builds. Rust core + MCP server.