Research and write from your own sources

LlamaIndex

MemoryData Wrangling

run-llama

Open-source data framework for building LLM and agentic apps over your own data, with 300+ integrations

ragvector-dbocr

Elasticsearch

CodingMemoryMonitoring

elastic

Distributed search and vector database used as the retrieval backend for RAG and agentic search

vector-dbsearchhybrid-searchrag

OpenViking

Memory

volcengine

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

ragcontext-databasevector-dbknowledge-base

Qdrant

CodingMemory

qdrant

Open-source vector database and similarity-search engine with filtering, hybrid search and a managed cloud.

vector-dbhnswhybrid-searchsemantic-search

Semantica

CodingMemory

semantica-agi

Open‑source framework for building semantic layers and context graphs for AI agents.

knowledge-graphgraphragprovenancesemantic-search

CocoIndex

Memory

cocoindex-io

CocoIndex turns codebases, PDFs, Slack, inboxes, and videos into a continuously updated.

data-indexingincremental-processingknowledge-graphsemantic-search

Framework

Haystack

Coding

deepset-ai

Open-source Python framework for building production LLM pipelines for RAG, search, and agents

ragsemantic-searchorchestrationdeepset

Latitude

Monitoring

latitude-dev

Latitude traces your agent in production, finds the failures, and dispatches your coding agent to fix them.

observabilityissue-detectiontelemetryevaluation

LanceDB

Memory

lancedb

Developer-friendly open-source embedded/serverless vector database for multimodal AI, built on the Lance columnar format for billion-scale retrieval.

vector-dbsemantic-searchmultimodalembedded-database

Chroma

CodingMemory

chroma-core

Open-source embedding/search database for retrieval and agent memory, self-hosted or cloud

vector-dbsemantic-searchhybrid-searchrag

Claude-Mem

Memory

thedotmack

Compresses Claude Code sessions into a local SQLite and Chroma memory store, queryable from other agents over MCP

sqlitevector-dbragcross-session

OpenRAG

CodingMemory

langflow-ai

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

ragdocument-processingsemantic-searchlangflow

Hindsight

Memory

vectorize-io

Agent memory system that stores and retrieves long-term memories so agents learn across sessions, not just recall history

long-term-memorydockerevaluationrag

Mnemosyne

Memory

mnemosyne-oss

SQLite-based memory layer for AI agents with hybrid vector and full-text recall and a tiered BEAM architecture

local-firstsqlitehybrid-retrievalsemantic-search

Neo4j

Memory

neo4j

Graph database used as agent memory and the store behind GraphRAG.

knowledge-graphgraphragvector-db

WeKnora

MemoryCoding

Tencent

Self-hostable document-knowledge framework combining RAG Q&A, a ReAct reasoning agent, and auto-generated wikis

ragreact-agentknowledge-basevector-db

HelixDB

Memory

HelixDB

HelixDB collapses Postgres + Qdrant + Neo4j into one Rust process on LMDB. Single access path: HelixQL queries, compiled

vector-dbknowledge-graphrag

MemPalace

Memory

mempalace

Local-first AI memory that stores conversations verbatim and retrieves them by semantic search over a structured, scoped index

vector-dbsemantic-searchlocal-firstcli

Cognee

Memory

topoteretes

Open-source AI memory platform that builds a self-hosted knowledge graph to give agents persistent long-term memory

knowledge-graphragvector-dblocal-first

LEANN

Memory

StarTrail-org

Stop storing embeddings, and still keep your recall. LEANN is a low‑storage vector index that recomputes embeddings on t

vector-dbraglocal-firstlow-storage

Superlinked Inference Engine (SIE)

InferenceDeploymentData Wrangling

superlinked

Self-hosted Kubernetes inference cluster serving LLMs, embeddings, rerankers, OCR and vision models with cluster-wide batching.

inference-serverkubernetesrerankingocr

TencentDB Agent Memory

Memory

TencentCloud

Local long-term memory for AI agents using a layered semantic pipeline and symbolic compression of tool logs

local-firstlong-term-memoryvector-dbrag

MemSearch

MemoryCoding

zilliztech

memsearch is not another claim that agents “need memory.” That layer is already crowded. The useful design choice is the

ragmilvushybrid-searchsemantic-search