Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) introduced JAZ, a minimalist agent framework that scored 70% on the StuLife long-term recall benchmark versus 62% f…
Kortexio released ContextMemory, an open-source self-hosted memory gateway that sits in front of any OpenAI-compatible /v1 engine such as llama.cpp, vLLM, Ollama, LM Studio or OpenAI and stores sessio…
Researchers at MIT CSAIL led by Zhening Li, Omar Khattab and Armando Solar-Lezama built JAZ, an agent framework whose only primitive is an LLM-backed `invoke` function that lets the model write arbitr…
Researchers built JAZ, a minimal LLM agent framework whose single primitive, invoke, lets the model write arbitrary executable code including recursive invoke calls, and reported that JAZ invoke outpe…
A developer surveyed setup documentation from six memory vendors — Mem0, Letta, Zep with Graphiti, Cognee, Supermemory and Mnemoverse — and found that npx performs five different jobs across them, onl…
A developer compared six agent memory systems — Mem0, Zep with Graphiti, Cognee, Letta, Supermemory and Mnemoverse — and found that in all six, graph edges are created on write, with only two walking …
A developer maintains @ghilteras/opencode-agent-memory, an experimental OpenCode plugin that gives AI coding agents persistent, editable memory stored as scoped Markdown files on disk rather than an o…
A developer surveyed six AI memory systems — Cognee, Mem0, Letta, Supermemory, Zep, and Mnemoverse — to determine whether any publish an input that accepts an explicitly negative verdict on a recalled…
AI agent memory is not a persistent brain but a combination of context windows, vector databases, and summarizers, according to an analysis of current architectures. Models like Claude Opus 5 and GPT-…
A developer introduced virage, a new tool that creates a searchable vector index of a codebase, complementing the previously released kms tool for capturing curated decisions. Virage uses AST-aware ch…
A developer has compiled a list of eight open-source tools for building AI agents with memory, including Statewave, Mem0, Graphiti, Cognee, LangGraph, and Letta. The tools are grouped by their functio…
Mnemoverse, a vendor on the list, published a decision map for choosing AI agent memory systems in 2026, arguing that the best choice depends on how much of the application the memory system should ow…
Achiral AI released Cognoscenti, a Rust-based benchmarking tool for cognitive memory systems, designed to evaluate how AI architectures select and forget memories rather than merely store them. The to…
Agent memory providers including Mem0, Zep, Letta, LangMem, Amazon Bedrock AgentCore Memory, Redis, Supermemory, and Cognee are converging on a common architecture that moves memory outside individual…
A developer benchmarking memory layers for Claude and MCP workflows reports that Zep outperforms Mem0 in LongMemEval benchmarks (63.8% vs 49.0%) due to its temporal knowledge graph, while ContextForge…
An engineer's investigation of Bench'd (benchd.ai), a self-described neutral benchmark authority for AI memory, reveals that its top leaderboard scores are not valid measurements. The engineer found t…
Persistent memory in AI agents introduces production-state risks that require data-system controls, according to a technical paper by an unnamed author. The paper cites examples such as a Mem0 issue w…
A developer's comparison of AI memory tools Mem0, Zep, LangChain Memory, and Letta reveals that real memory requires conflict resolution, not just retrieval. Mem0 uses a two-stage LLM call to add, upd…
Nous Research pitched its Hermes Agent as a control plane that users should own, arguing the durable asset is the harness rather than any single model. The MIT-licensed, self-hosted runtime, released …
A single governed context layer, such as Atlan's Nexset, can resolve discrepancies in agent answers by providing one shared definition, as illustrated by three different AI coding assistants returning…