Agent memory

Captures a team's real engineering conventions, rejected approaches and edge cases as versioned Markdown decision files in a repository, so a coding agent consults them before writing code.

• Agent memory

A local-first memory layer for AI assistants that runs an MCP server over a local SQLite file, so tools such as Claude Code, Cursor and GitHub Copilot can share durable memory about a user, their work and past decisions.

• MCP servers
• Agent memory

An agent-native database that stores memory, state, events, artifacts and relations as first-class objects, returning structured evidence instead of plain top-k text matches.

• Agent memory
• Databases

A TypeScript retrieval framework for AI agents that structures multi-source knowledge as resources, chunks, entities, facts and access-controlled evidence in a knowledge graph, instead of treating a corpus as a flat vector index.

• Agent memory
• RAG

A research environment that wraps a frozen language model in a persistent identity, memory, trust and governance loop, testing whether an agent's capability can come from surrounding structure rather than model weights alone.

• Agent frameworks
• Agent memory

A local-first retrieval-augmented knowledge base for the Pi and OMP coding agents, combining semantic embeddings with BM25 keyword search and code-aware chunking over a codebase, docs, PDFs and notes.

• Agent memory
• RAG

A durable, Git-versioned operating-memory layer for coordinating Codex, Claude Code and other agents on top of the Multica live-collaboration platform, distributed as an installable skill pack.

• Agent skills
• Agent memory

A file-based shared memory for AI coding tools that keeps tasks, bugs, plans and constraints synchronized across different agents and editors, so planning in one tool and coding in another loses nothing.

• Agent memory

A user-owned personalization memory layer for AI agents that models a person's preferences, habits and communication style as a fuzzy graph, with a deterministic zero-LLM core and optional human-approved enrichment.

• Agent memory

A command-line interface and MCP server that gives AI coding agents a local, cited memory layer for a Git repository, built from generated wiki pages, symbol context, git history and dead-code and risk signals.

• MCP servers
• Agent memory

A collection of curated AI agent skills for coding assistants, paired with a local semantic search engine over those skills powered by the Gemma embedding model, with no API keys or cloud dependency.

• Agent skills
• Agent memory

A single-binary code intelligence tool that builds a persistent, source-grounded knowledge graph of a repository, so a coding assistant can look up dependencies, predict change impact, select relevant tests and verify refactors without rediscovering the codebase each session.

• MCP servers
• Agent memory

A self-hosted MCP server that gives AI coding assistants a persistent, searchable knowledge base of architectural decisions, specs, plans and lessons learned, shared across projects and multiple agents.

• MCP servers
• Agent memory

Context infrastructure for AI coding agents that combines tree-sitter code chunking, LanceDB vector search and SQLite full-text search into hybrid retrieval and persistent project memory, exposed as a CLI, MCP server or library.

• MCP servers
• Agent memory

A self-hosted semantic code-search platform, invoked as cix, that indexes a codebase into a vector store for meaning-based search, combining hybrid BM25 and dense embeddings through an embedded llama.cpp server.

• Agent memory
• RAG

An MCP server that gives coding agents such as Claude Code and Cursor reviewable shared memory, working locally with zero configuration or connecting to Novyx Cloud for governed, approvable actions and audit trails.

• MCP servers
• Agent memory

A modular Rust library for building durable AI agent memory systems, combining B-Tree, BM25 full-text and HNSW vector indexes in one embedded, schema-aware document database.

• Agent memory
• Databases

This benchmark compares three memory architectures for multi-agent LLM systems - raw conversation history, vector-only RAG, and a structured context graph - on questions that require combining facts from different points in a conversation, using no LLM calls.

• Agent memory
• AI evals

AsterVec is an embeddable, disk-based vector search engine for on-device AI agent memory and local RAG, keeping only a small navigation structure in RAM so it can search millions of embeddings within a few hundred megabytes of memory.

• Agent memory
• Databases

Gomaa is a local-first, hierarchical memory engine for autonomous AI agents that stores memories as human-readable Markdown notes in an Obsidian vault, backed by PostgreSQL with pgvector or zero-config SQLite, so a person can audit and edit what an agent has learned.

• Agent memory

Cursor History MCP is an MCP server that lets an AI assistant search, inspect and export a user's existing Cursor chat history, turning months of past decisions, bug fixes and architecture discussions into context the assistant can query.

• MCP servers
• Agent memory

Synaptic Memory is a knowledge-graph and MCP tool server for LLM agents that builds a graph of documents, chunks, database rows and their relations instead of only chunk embeddings, so an agent can follow relations rather than rely on similarity search alone.

• MCP servers
• Agent memory

RASPUTIN is an archived research codebase exploring long-term conversational memory for LLM agents, partitioning retrieval across four fact-type lanes and reranking with a cross-encoder, published for its architectural findings rather than as a production system.

• Agent memory

zerikai_memory is a standalone, local-only Python MCP server that gives any IDE persistent, workspace-isolated memory of a codebase's entities, built with deterministic tree-sitter parsing rather than an LLM-driven index.

• MCP servers
• Agent memory