"Fluent Bit" matching MCP servers:

Enables AI agents to search, share, and vote on community knowledge solutions via the Reposit platform.

Enables ChatGPT Developer Mode to answer questions using operator-defined instructions, with tools to set and retrieve those instructions via a local Streamable HTTP MCP server.

Enables Codex, ChatGPT, and Aside to share project work memory by reading private GitHub-backed checkpoints and searching or re-reading allowed local/SSD documents through read-only MCP tools.

Enables MCP-speaking agents to search, read and write cards in a folder-based knowledge store and to capture decisions as proposals awaiting the owner's confirmation, with a small CLI for systems that can only run commands.

Enables AI coding tools and developers to store, search, and supersede durable engineering discoveries with temporal validity, and to coordinate active work across sessions via MCP.

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.

Hosts three live read-only MCP servers enabling agents to retrieve and cross-reference curated fictional and real archives with provenance and source URLs.

MCP server that provides tools to search and retrieve skills, badges, and evidence from the Gaia Skill Tree registry.

Official MCP server for creating, reading, and updating mind maps on coret.id from AI agents. Changes appear live in the Coret editor.

Enables agents to traverse a FalkorDB service graph by reading topology and open incidents, running graph algorithms, and executing multi-hop root-cause investigations whose LOCATE, SUGGEST and PROPOSE stages persist as resumable traces. It also surfaces episodic memories and searches runbooks and ownership records, while keeping raw Cypher, tenant switching, approvals and simulation out of reach.

Enables AI assistants to record decision summaries when suggestions are rejected or corrected, and to search past decisions in later sessions so users do not repeat the same corrections.

Turn any website into a book you agent can read

Enables AI agents to run automated daily code reviews, retrieve Markdown reports, and curate a project knowledge base across any Git repository.

Enables voice assistants to research and rank family outings by checking live web sources, hourly forecasts, park alerts, and drive times against each household member's needs. It remembers family profiles and past visits so every recommendation comes back with a per-member fit verdict.

Reduces token waste by caching code understanding in .mi context files and prevents agent conflicts by coordinating intent and file access across sessions.

A persistent, PostgreSQL-backed repository management system and semantic memory MCP server that stores the entire Git DAG natively in PostgreSQL with temporally-decayed semantic vector embeddings for AI IDEs.

Enables creation of persistent, compounding knowledge bases using Karpathy's LLM Wiki pattern with LLM-maintained markdown wikis. Supports automated ingestion, cross-referencing, synthesis, and linting of sources as an alternative to traditional RAG systems.

Repository-native, Git-reviewable memory extension for AI coding assistants to persist project context across features, using SQLite caching for up to 10x token reduction.

An MCP server that captures the rationale behind code changes at the moment they are written, binding decisions to commits with full provenance, and serves that context later without guessing. It records 'why code exists' and tracks anchor health over time.

Belief-tracking memory for AI agents. Remember, recall, and ask why: every memory carries evidence, contradictions are surfaced, and retracted facts take their conclusions with them. Zero dependencies, local, MIT.

Enables querying company knowledge base using RAG, providing accurate answers from internal documents via MCP.

Enables querying a local wiki through MCP-style tools, including search, Q\&A, and knowledge map, with a web viewer for human browsing.

AI reads your codebase like a book - one page at a time. Pharaoh gives it the index and a map of how every chapter connects.

An AI conversation management layer that enables creating chat sessions, persisting message history to GitHub, and performing semantic searches over past interactions. It supports multi-turn threading and context injection to integrate external memory sources into Claude conversations.

Enables Claude Desktop and Claude Code to build, update, inspect, validate and compile workflows for the SOLVE-IT Workflow Builder from natural language, automatically laying out nodes and connections and checking them against the SOLVE-IT knowledge base. Each result is written as a JSON file for import into the builder, or returned as a share link when small enough.

A provider-neutral MCP server that provides tools for managing skills, agents, references, and artifact memory in a local workspace.

Enables AI assistants to save resolved debugging sessions as concise experience cards into a local JSON knowledge network, and to retrieve relevant past cards when new bugs arise. It also powers a spaced-repetition review interface to reinforce memory of those experiences.

Enables evaluation of local models by giving each agent session its own sandboxed wiki folder where the model ingests sources, creates and cross-links pages, answers questions, and lints its notes, with the results graded as an Obsidian vault.

Enables MCP clients to discover and fetch skills, agents, commands, and hooks from the Gen-e2 Lab Registry, and check local inventory compliance against the registry.

Enables project-scoped agent memory backed by a per-project SQLite index and raw data store, plus a global registry for discovering local memory workspaces. Agents can search summaries, retrieve original records on demand, save new memories, and link related records without sharing memory across projects.