A developer warns that LLM memory systems in production fail silently because retrieval quality degrades while dashboards remain green. The analysis cites benchmarks showing leading systems score 92.5…
FalkorDB argues that preventing LLM hallucinations in RAG systems is a retrieval-layer problem, not a model problem, and that vector-only retrieval fails at grounding due to context fragmentation, rel…
On August 3, 2026, at Frontier Tower in San Francisco, the Memory Meets Motion hackathon showcased projects built on FalkorDB, RocketRide.ai, Guild.ai, and LaserData, with Atrium winning first place o…
Lettria, a knowledge graph vendor and AWS Partner, benchmarked graph-structured RAG against vector-only retrieval across four domain corpora and reported correctness improving from roughly 50% to abov…
FalkorDB's GraphRAG SDK is positioned as a key tool for network analysis applications in 2026, with ten production use cases including knowledge graph construction for RAG, fraud ring detection, and s…
FalkorDB released a community node for n8n that integrates GraphRAG, enabling AI agents to query a knowledge graph built from GitHub-hosted documentation. The node exposes five graph tools, allowing a…
FalkorDB has rewritten its core database engine in Rust, replacing the original C codebase with 80,000 lines of Rust, 357 merged pull requests, and passing 1,585 TCK scenarios and 1,322 flow tests. Th…
FalkorDB CEO Guy Korland will demonstrate how to power agentic workflows with a knowledge graph for n8n and LangGraph/LangChain, addressing the fragmented data problem by combining documents, APIs, an…
Python's graph ecosystem spans analysis and machine learning, with NetworkX as the default for prototyping and smaller jobs, while python-igraph, graph-tool, and NetworKit offer higher performance for…
Hikari Systems released Slater v0.24.1, a low-memory graph database designed for read-heavy graphs that can serve hundreds of millions of nodes and billions of edges from a few hundred MB of RAM by pa…
Four open-source projects—Graphiti, Hindsight, Mem0, and others—offer expanded memory capabilities for AI agents and large language models, using techniques like temporal knowledge graphs and multi-st…
ActiveGraph v1.2.0 is now live, introducing a pluggable graph projection seam with FalkorDB as the first external backend, achieving up to a 30x speedup on structural queries. The release, driven by e…
A developer identified two necessary conditions for FalkorDB's db.idx.vector.queryNodes to work properly: data must be stored as a vector type using vecf32() and a vector index must be created. Common…
Commonplace launches a self-hosted, privacy-tiered memory system for AI agents, using a two-tier Graphiti knowledge graph that runs entirely on local hardware by default, with a personal tier optional…
Nate Scott released Context Graph Agent (CGA) version 1.30.47, a local-first graph context service that reduces prompt tokens by 90.44% and lowers hallucination pressure by 13.34% for AI coding agents…