AI and memory

Deterministic context selection for AI coding agents. Local memory that compounds across sessions.

Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search

MCP server for AI-powered image recognition and description using OpenAI vision models.

RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.

MCP server for AI-powered image recognition and description using OpenAI vision models.

Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

Local-first, LLM-agnostic memory layer for AI assistants.

Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.

Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.

E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.

Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.

35Trust score 35 of 100, Limited

Issue tracker and durable project memory for your coding agent, scoped to the folder you open.

35Trust score 35 of 100, Limited

Local-first image, vector and document toolkit that measures its own output. Nothing uploaded.

Portable AI memory shared across models and harnesses - plain markdown you own.

Durable, versioned memory for AI assistants. Remote memory needs a Pastepile subscription.

Persistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB.

35Trust score 35 of 100, Limited

Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents.

Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.

Save up to 80% tokens when AI reads code via AST-aware structural reading

34Trust score 34 of 100, Limited

Cross-platform shared memory and ticket coordination for AI agents across MCP clients.

Docs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.

Local-first multilingual, auditable memory for Codex, Claude Code, and MCP clients.