"Current Weather in Beijing" matching MCP servers:

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Lets MCP clients search vetted public listings and their own private library of coding-agent sessions, load a saved session as bounded starting context, and save the current transcript privately, reusing an existing command-line sign-in. Sessions are scrubbed and framed as untrusted reference material, and acquiring a paid listing never completes a purchase automatically.

Enables agents to retrieve their current identity from IDENTITY.md and route durable lessons, preferences, rules, and corrections to the appropriate standing file over MCP stdio.

Persistent AI agents memory for Claude, Codex, Cursor... that is always current.

Enables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.

Enables MCP clients to discover folder-bound projects, search stored project memory, retrieve current handoffs, and propose new knowledge for human review, while approval stays in the local workbench.

Serves project memory to AI agents, providing task-scoped context, tracked changes, validation evidence, and history to keep modifications grounded in current project facts.

Stores architectural decisions in a SQL database for persistent AI agent memory, enabling cross-session continuity and duplicate detection.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Enables agents to record facts with declared sources, search or list current and superseded memories, and correct entries while preserving version history and rejecting stale writes.

Enables AI agents to read and write a bitemporal context graph per end-customer through five MCP tools, so they can query current or historical facts, explore relations, and record learned information with provenance.

A local stdio MCP server that exposes a shared brain (read/search/write) over ~/.claude/memory, allowing memories written in any agent to be readable and searchable across all three (Claude Code, Cursor, Codex). It provides tools like memory_search, memory_read, memory_write, etc., with no external services.

Enables people and AI assistants to share one persistent Markdown-in-Git memory, so any MCP client can load current context, save sessions and decisions, search notes, and work from a team's real knowledge across machines.

Provides MCP tools that give AI agents persistent, append-only memory in a git repository, letting them record observations, decisions, and corrections while retrieving context briefs, current facts, conflicts, and traceable event history without a vector database.

MCP server that maintains cited, current answers to standing research questions by tracking chosen sources, consolidating repeated coverage, and providing evidence-based briefs with change signals.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Provides tools to slice documentation by headers, append git-verified session entries, and retrieve the current phase to manage context for AI coding agents.

MCP server that provides programmatic access to the SOLVE-IT digital forensics knowledge base, enabling LLMs to query, navigate, and search forensic techniques, weaknesses, mitigations, objectives, and citations.

Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost.

Resonance Detection MCP server that proactively finds cross-domain pattern matches between the current problem and past experiences.