Context, Memory & RAG

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding

Local-first AI memory system that stores conversation history verbatim and retrieves it with semantic search through a structured palace architecture (wings, rooms, drawers). Achieves 96.6% R@5 on LongMemEval with zero LLM calls, making it the best-benchmarked open-source memory layer for agents that need cross-session persistence without cloud dependencies

Agent memory system organized around three explicit operations—retain, recall, and reflect—with semantic, keyword, graph, and temporal retrieval plus an MCP server. The June 2026 release and production usage make it a concrete reference for turning cross-session persistence from passive storage into an active learning layer inside the harness

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

ByteDance/Volcengine's open-source context database that puts an agent's knowledge, memory, and skills in one virtual filesystem under viking://, navigated with ls/tree/read/grep and inspectable by humans instead of hidden in an embedding store. Every directory carries generated L0 abstracts and L1 overviews so agents read summaries before opening full content (L2), retrieval is scoped to a direct

A library for efficient similarity search and clustering of dense vectors

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want

A modular graph-based Retrieval-Augmented Generation (RAG) system

Vector Search Engine and Database for the next generation of AI applications. Also available in the cloud

Tencent's fully local agent memory system with a 4-tier progressive pipeline (Conversation → Atom → Scenario → Persona) and symbolic short-term memory via Mermaid canvases. The benchmark data is striking: 61% token reduction and 51% relative pass-rate improvement on long-horizon tasks, demonstrating that hierarchical memory architecture outperforms flat vector stores for coding agents

Persistent memory server for coding agents that retrieves only the top-K relevant observations via hybrid BM25 + vector + graph search instead of loading a whole memory file into context (~1,900 vs 22K+ tokens at 240 observations, 92% fewer). Reports 95.2% R@5 on LongMemEval-S with a local embedding model, plus a reproducible eval harness to check that claim. One server serves 20+ agents (Claude C

OSS embedding database. Fastest way to build RAG

Google Labs' specification for describing visual identity systems to coding agents: machine-readable design tokens (YAML front matter) combined with human-readable design rationale (markdown prose) give agents a persistent, structured understanding of design constraints without requiring custom tool chains

The reference architecture for stateful agents: three-tier memory (core / archival / recall) maps directly to harness state management design. Their agent loop redesign post is the most thorough public analysis of how memory structure shapes the harness

Git for Data

"RAG-Anything: All-in-One RAG Framework"

Open-source vector similarity search for Postgres

LocalGPT is an open-source project for secure, private interactions with documents locally, featuring comprehensive model support, embeddings, API for RAG applications, and GUI options, with a focus on privacy and local data processing github

LangChain's CLI that writes and maintains agent-readable wikis for codebases or purpose memory, turning documentation drift into a versioned, automatable harness artifact. Emits Google Open Knowledge Format bundles so curated context stays portable across agents and can be kept fresh via CI

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Weaviate is an open source vector search engine that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients

Data Version Control - Git for Data & Models - ML Experiments Management

A distributed POSIX file system built on top of Redis and S3

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Build AI-powered semantic search applications

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

An ETL framework for AI that transforms data into embeddings and knowledge graphs, with incremental processing to recompute only what changed and keep indexes fresh

The transactional alternative to Elasticsearch, built on Postgres

Stream large multimodal datasets to achieve near 100% GPU utilization. Query, visualize, & version control data. Access data w/o the need to recompute the embeddings for the model finetuning

Storage layer that brings scalable, ACID transactions to Apache Spark and other engines

Memory library for building stateful agents

Persistent memory for AI coding agents delivered as a single Go binary with SQLite + FTS5 and 18 MCP tools for save, search, session lifecycle, and conflict detection. The agent-agnostic, zero-dependency design makes cross-session memory a local harness primitive rather than a managed cloud service

An open source python framework for automated feature engineering

An open source feature store for machine learning

Modern columnar data format for ML implemented in Rust

Microsoft Research's prompt compression toolkit (up to 20x compression, minimal performance loss) that can be embedded as a preprocessing step in the context delivery layer. LLMLingua-2 adds 3–6x speed gains, making it viable for latency-sensitive agent loops

An easy way to turn any app into searchable data for LLMs

Code search primitive that replaces grep+read cycles with natural-language retrieval, cutting active tokens by ~98% while keeping 99% of a transformer-based retriever's accuracy. Ships as an MCP server and CLI, runs on CPU with zero external dependencies — the right drop-in for any coding agent harness struggling with context pressure

Pachyderm is a version control system for data

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

Git-like capabilities for your object storage

Tensor search for humans

Purpose-built agent memory store with automatic conversation summarization, entity extraction, and semantic search over session history. Solves long-session context overflow at the memory layer rather than forcing the harness to manage trimming manually

The AI-native database built for LLM applications, providing incredibly fast vector and full-text search

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

Agent Package Manager

Easiest and laziest way for building multi-agent LLMs applications.

Mounts S3, Slack, Gmail, GitHub, and Redis side-by-side as a single virtual filesystem so agents interact with every backend through familiar bash commands instead of learning N distinct APIs. The key harness insight: LLMs are already fluent in grep, cat, and cp — leveraging that vocabulary eliminates tool-schema bloat and makes cross-service pipelines compose as naturally as local shell scripts

Agents that self-improve with experience

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

NVIDIA's September 2026 extension for the Pi harness that packages four efficiency mechanisms discovered by running 152 candidate ideas through auto-research loops: Action Fusion (an edit runs its follow-up validation in the same tool call), ObservationPack (repeated large tool results become stable handles with exact paged recall), an Evidence-Preserving Reducer (long logs compact to receipts onl

distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.

AST/tree-sitter code search MCP server that indexes a codebase and returns compact, relevant snippets to reduce coding-agent context usage

Bitterbot - a mesh of agents that turns shared experience into collective capability.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

A distributed system for embedding-based vector retrieval

AI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-ready.

书童 Pagekin（原名 AI 小说作家）：开源免费的 AI 长篇小说写作桌面软件，从设定、蓝图到正文、审稿、定稿；支持拆解仿写、续写、改写，可导入写作 Skill（如去 AI 味）。模型需自行配置，作品在本地。Pagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS.

Vector database plugin for Postgres, written in Rust, specifically designed for LLM

Fractal Graph-of-Thought. Rhizomatic Mind-Mapping for Ai-Agents, Web-Links, Notes, and Code.

The Virtual Feature Store. Turn your existing data infrastructure into a feature store

Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs

Turns agent-learned project knowledge into a repo-local, symbol-grounded wiki with drift detection and task-aware routing. The critical gap it fills: most agent memory stores facts, but mex keeps those facts connected to the exact code symbols they describe and flags when code changes invalidate them — making memory freshness a harness-level concern rather than a manual cleanup task

A Highly Scalable Distributed Vector Search Engine

A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable

Declarative multimodal AI data engine for versioned tables, computed columns, and vector search

by activeloopai - Hivemind turns your traces into reusable skills across agents

Self-improving executable context layer for data and analytics agents: it ingests warehouses, BI tools, and wikis to build a semantic layer with approved metrics, joinable columns, and resolved fan/chasm traps, then serves the result to Claude Code, Codex, and Cursor through MCP. Fills the gap where general-purpose agents invent metric logic on every question — it turns warehouse querying from a p

Coding agent harness optimized for surgical context curation and API cost reduction: Hash Anchored edits, massively parallel operations, and AST manipulation combine to cut costs 50–80% while improving code quality. Demonstrates that precise context delivery — not just bulk compression — is the right lever for efficient coding agents

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

A self-organizing data hub for S3

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

Turns raw Claude Code sessions into a self-evolving knowledge base: hooks capture every interaction, the Agent SDK extracts decisions and lessons, and an LLM compiler distills them into structured, cross-referenced articles that improve retrieval quality over time. The most concrete open-source implementation of trace-driven memory evolution for coding agents

Repository-level operating harness that turns any software repo into an agent-ready workspace: structured AGENTS.md, HARNESS.md, and FEATURE_INTAKE.md give agents the missing project context — where to start, what the product contract says, how risky the change is, and which decisions future agents should inherit. The most concrete open-source implementation of "coding agents need better repositor

Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

Self-updating repo wiki for AI coding agents that tracks project conversations and context locally, lives in your repo, and is free to use

A 10x faster, cheaper, and better vector database

Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

Self-hosted persistent memory layer with an 8-stage consolidation pipeline (episodes → facts → relationships → patterns) and built-in MCP server. The critical gap it fills: production-grade cross-session memory without cloud dependencies or complex infrastructure — a single Docker Compose gives you Postgres, pgvector, and background consolidation

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

A Python vector database you just need - no more, no less

🔥🔥🔥 Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.

A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.

AI-powered IDE for novel writing — local LLM + RAG, privacy-first, BYOK. For web fiction authors and creative writers.

by David Corvoysier - Durable cross-agent memory for Claude Code, Codex, pi, and Hermes. Your memory is a Hugging Face dataset you own: recall it from any machine or share it with your team. Single binary, local index, pinned local embedding models

AI equity research agent with resilient workflows, evidence-grounded RAG, versioned reports, and automated quality evaluation.

Governed shared memory for AI agent fleets, with multi-agent and multi-tenant support, MCP integration, trust tiers, audit trails, knowledge graph capabilities, and self-improving retrieval

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.