Cognitive infrastructure for AI agents. A persistent, portable cognitive layer that travels with your agents — provenance, confidence, and temporal awareness baked into every assertion.

The cognitive layer for AI coding agents — evidence-backed ship reports, blast-radius protection, and persistent project memory. Works with Claude Code, Codex, Cursor, and any MCP client.

The persistent cognitive layer for AI-assisted development. Gives AI agents the project context that currently only exists inside a senior engineer's head.

mindshape — a memory-native cognitive layer for agents, built on the memshape contract. Name reserved for imminent release (July 2026).

Production AI agents for Toolpack SDK — 8 channel integrations (Slack, Discord, Telegram, SMS, Email, Webhook, Scheduled, MCP), AgentMind persistent cognitive layer (goals, beliefs, reflections), interceptors, evals, and multi-agent coordination

MCP server that exposes Tools agents as MCP tools with cognitive layer

Microsoft Cognitive Services Speech SDK for JavaScript

A cognitive layer for Cursor's AI agent: lossless token savings via a content-addressed evidence store, plus verifiable semantic memory, project world model and skill runbooks. Fully local, zero telemetry. | 给 Cursor agent 的认知层：内容寻址证据库无损省 token；可验证语义记忆、项目

Sovereign cognitive-middleware layer for OIS agents — pluggable chain-of-responsibility augments for tool-call interception, caching, dedup, description enrichment, error normalization, and telemetry. Consumed by @apnex/network-adapter via opt-in config.

Shared cognitive layer for co-coding teams — agent coordination, decisions, and knowledge

A portable cognitive layer for AI agents — intention-driven memory recall, a typed meaning layer (artifacts), provenance, and an inspectable agent runtime. Bring your own store, embeddings, and LLM.

Pluggable cognitive layer — port of GCS v15.3 as an embeddable MCP cognitive kit. Provides reasoning, research, planning, creativity, reflection, security, knowledge, analysis, agency orchestration, and adaptive pipelines via MCP protocol.

This is an internal utility, not intended for public usage.

Polyfill Web Speech API with Cognitive Services Speech-to-Text service

A portable cognitive layer for AI agents — intention-driven memory recall, a typed meaning layer (artifacts), provenance, and an inspectable agent runtime. Bring your own store, embeddings, and LLM.

Cognitive layer for AI agents — router, reasoner, supervisor, executor. Works standalone with built-in mocks; opts into real services when you have them.

An isomorphic client library for Azure OpenAI Assistants.

Wrapper around the Botpress Client to call LLMs

Parse CSS Cascade Layer names.

An icon is a symbol representing a command, device, directory, or common action.