"Building a solid memory base for AI development" matching MCP servers:

Provides AI coding agents with a local, Markdown-first shared memory, enabling them to record decisions, failures, progress, and handoffs and retrieve them across sessions via MCP tools.

Provides a shared, persistent memory layer for AI assistants, letting them read and write to a local Obsidian vault through MCP with validation, secret rejection, and deduplication.

Enables AI assistants to retain memory across sessions by storing conversations locally in Markdown files, allowing personalization and continuity without external servers.

Enables agents to search, read, list, and amend a git-backed markdown knowledge base, automatically committing and publishing changes.

Enables Codex and Claude to share Git-backed Markdown memories, assistant handoffs, and reusable skills through read-only and write-enabled MCP endpoints, while owners review revisions, conflicts, and deletion requests in a private GUI.

Persists Claude Code sessions to Notion as team memory, enabling queryable recall of decisions, work state, and project architecture.

A personal knowledge base MCP server that allows AI assistants to manage notes, tasks, and ideas through tools, resources, and prompts.

Enables AI agents to share a persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from sources like Obsidian vaults, code, and transcripts through MCP and REST APIs. Provides token-optimized, tiered retrieval with full-text and semantic search so every agent session builds on accumulated context.

Enables AI agents to capture, classify, synthesize, and retrieve persistent shared knowledge from sources such as Obsidian, code, transcripts, bookmarks, and sessions. It provides token-efficient search, context briefings, and tiered memory through MCP and REST APIs.

Enables AI agents to share a persistent, self-learning memory by ingesting and classifying knowledge from Obsidian, code, transcripts, bookmarks, and terminal sessions, then retrieving token-optimized context through MCP and REST APIs.

Enables AI agents to share persistent memory by capturing, classifying, synthesizing, and retrieving knowledge through token-optimized, three-tier retrieval with hybrid keyword and semantic search. Supports bidirectional Obsidian sync, session and bug-fix capture, and a self-learning loop that compounds context across sessions.

Enables AI agents and clients to capture, classify, synthesize, and retrieve persistent knowledge from multiple sources through MCP and REST APIs, with tiered memory and token-optimized context.

Gives AI agents a shared persistent memory by ingesting Obsidian vaults, code, transcripts, web clips, and session or bug-fix captures, then serving token-optimized context briefings, keyword and semantic search, and cross-source synthesis. Enables multiple agents to read and write the same growing knowledge base so each session builds on the last.

A lightweight personal knowledge base MCP server that lets clients store, search, organize, and summarize research notes from a local JSON file.

Enables AI agents to share persistent memory by ingesting, classifying, synthesizing, and retrieving knowledge through MCP and REST APIs, with token-optimized, tier-aware search and Obsidian sync.

Enables AI agents to share a persistent, self-improving memory by ingesting sources like Obsidian vaults, code, transcripts, and session captures, then serving them back through search, classification, synthesis, and token-optimized context briefings. It lets multiple agents read and write the same knowledge base, so each session builds on the last without copy-pasting context.

Gives AI agents a shared persistent memory by ingesting notes, code, transcripts, bookmarks, and session captures into a SQLite FTS5 knowledge base they can search, read, classify, promote, and synthesize over MCP. This lets multiple agents retrieve tiered, token-optimized context and compound what they learn across sessions instead of starting from zero.

Enables AI agents to share persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from Obsidian vaults, code, documents, transcripts, bookmarks, and sessions through MCP and REST interfaces with token-optimized search.

Enables AI agents to capture, classify, synthesize, and retrieve persistent knowledge from sources like Obsidian, code, web clippings, transcripts, bookmarks, terminal sessions, and fixes, using FTS5 and semantic search through MCP and REST interfaces.

Enables AI agents to share persistent memory by capturing, classifying, synthesizing, and retrieving knowledge from sources like Obsidian, code, and transcripts via MCP and REST APIs. Provides token-optimized search, three-tier memory, and self-learning capture of sessions and fixes so multiple agents can build on prior context.

Enables AI agents to capture, classify, promote, synthesize, and retrieve persistent knowledge from sources such as Obsidian vaults, code repos, YouTube transcripts, bookmarks, terminal sessions, and bug fixes. Exposes tiered cold/warm/hot memory with token-optimized search, context briefings, and cross-source synthesis so multiple agents share one compounding brain across sessions.

Enables AI agents to capture, classify, synthesize, and retrieve persistent knowledge through MCP and REST APIs, with SQLite FTS5 search, tiered memory, and token-optimized context so multiple agents share and compound context across sessions.

Enables AI agents to share persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from sources such as Obsidian vaults, code, transcripts, bookmarks, and terminal sessions through MCP and REST APIs.

Enables AI agents to capture, classify, promote, synthesize, and retrieve persistent knowledge from sources like Obsidian vaults, code, transcripts, and session logs, serving it through MCP tools and a REST API. Provides tiered, token-optimized memory so multiple agents share one compounding brain instead of starting from zero each session.

Gives every AI agent a shared, persistent memory by ingesting Obsidian vaults, code, transcripts, bookmarks and terminal sessions into a three-tier SQLite FTS5 store, then serving token-optimized hybrid retrieval, classification, promotion and cross-source synthesis over MCP and REST. This lets multiple agents read from and write to one compounding brain so each session starts with better context than the last.

Enables AI agents to persistently capture, classify, synthesize, and retrieve knowledge across sessions through MCP and REST interfaces, using tiered memory and token-optimized search. It also syncs Obsidian vaults and supports self-learning from sessions and fixes.

Enables AI assistants to retain, review, approve, and retrieve encrypted local notes, decisions, preferences, and follow-ups across sessions, with retained source evidence and correction history.

Lets AI clients store, retrieve, update, and forget long-term facts in a local SQLite database with deterministic lexical search, sharing the same memory across multiple clients without relying on model APIs or embedding services.

A notes app that becomes your second brain. Open source, private, encrypted when you want it, and every file stays yours. Mac, Windows, Linux and self host!

Enables AI assistants to maintain a persistent, local memory using SQLite with ranked full-text search, German morphological matching, and two-axis filing, all without external services.

Automatically records AI conversation turns and code changes to local Markdown files to provide persistent context across chat sessions. It enables AI agents to search history through MCP tools and provides a web viewer for browsing past discussions.

Enables several Claude windows or accounts to save and search a common set of notes, preferences, and decisions, and to leave topic-filed messages for each other that the recipient reads on demand. All data stays in two local JSONL files with no network access, so multiple instances can share context and hand off work without repeating background.

Enables persistent memory for Claude Code sessions by recording observations and building knowledge graphs for cross-session learning and domain knowledge management.

Provides cross-session persistent memory for coding agents via MCP tools to store, retrieve, and manage notes with hybrid keyword/semantic search and automatic deduplication.

Stores markdown knowledge notes in SQLite or Postgres and exposes them to AI agents over MCP, letting agents read individual sections, search, and write updates transactionally. Each write is validated, and anything that introduces broken links, missing summaries, or duplicate text is rolled back with a reason.

A local shared-memory MCP server for Claude, Codex, Hermes, and other MCP-aware agents, providing a durable memory layer with Markdown files and SQLite fact store.

A local MCP server that provides agents with tools to list, read, search, inspect history and diffs, and capture unstructured text in a user-owned Git repository of durable memory.

Local-first agentic knowledge layer over Obsidian notes, enabling MCP-aware agents to search, retrieve, and compile knowledge with provenance and task contracts.

Enables users to create and control portable, user-owned memory archives, including saving memories, reflections, values, and stories, exporting them as open JSON, publishing or discovering public archives, and loading consented material as a clearly-labelled memory-based AI persona.

Enables read-only cognitive retrospect over Obsidian notes, surfacing stance changes, verifying claims with citable evidence, and avoiding unfounded causal stories via hybrid retrieval and eight read-only MCP tools.