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 …
LoopX, a stdlib-only Python project from ex-ByteDance engineer Ruiteng Huang, has gained 4,800+ GitHub stars since May by keeping agent state outside the runtime, using a CLI and file-backed store to …
Letta launched the Letta Agents SDK, a TypeScript library for building stateful, persistent agents that retain identity, memory, and state across different machines and backends including Letta Cloud,…
A developer's evaluation of three agent memory frameworks—file-based, structured store, and reinforcement-learning-trained experience—found that the file-based approach, as implemented in OpenClaw's m…
AI agent memory has become a crowded corner of AI infrastructure funding in 2025 and 2026, with startups like Letta, Mem0, and Zep building persistent memory systems on vector databases and retrieval …
A new benchmark study from a40-labs measures three shapes of agent memory—file-based curation, structured stores, and trained experience—and finds that the file-based approach used by Claude Code, Cli…
Semvec, a semantic memory system from Versino PsiOmega, achieves near-mem0 quality on the LOCOMO benchmark with zero generative-LLM calls at ingest, reducing context tokens by 87% and ingest time by ~…
Researchers introduced AgentMemBench, a benchmark evaluating five long-term memory strategies for conversational AI agents across three datasets and 491 annotated question turns, finding that external…
Letta released the open-source trajectory package on July 24, 2026, a standard format for recording coding-agent sessions across harnesses including Claude Code, Codex, and Letta Code. The package red…
A developer's analysis of AI memory deletion reveals that consumer AI assistants like ChatGPT and Claude allow users to delete individual memories through settings panels, but cannot prove the underly…
A developer testing a support-agent LLM with a memory layer found that the agent retrieved the correct fact (user on enterprise plan) but still responded with an incorrect suggestion to upgrade to ent…
A developer has created PVM (Persistent Vector Memory), an open-source Python library (~800 lines) that gives LLMs long-term memory without API keys or GPUs. It uses temporal weight decay, delta rule …
The term 'Agent Development Environment (ADE)' has two distinct meanings in 2026: Letta's original sense of a platform to build and debug agents themselves, and a newer sense, popularized by Orca, of …
Perseus Computing LLC released Mimir, a local-first, encrypted memory engine for AI agents as a single Rust binary with zero dependencies. The open-source tool provides persistent memory across sessio…
Markdown files are a legitimate pattern for agent memory in single-agent, single-user scenarios, but the approach breaks at scale, under concurrent agents, and as facts change and errors compound. Com…
A developer built Lorekeeper, an open-source memory layer for AI agents that uses idle-time reflection cycles to prune, merge, and link memories. The system achieves 84.6% Recall@1 and 96.6% Recall@5 …
A developer compares four agent memory systems—Letta, Mem0, Graphiti, and Cognee—highlighting their approaches to knowledge graphs and long-term memory for AI agents. The analysis covers each system's…
The tech industry shipped four types of memory systems this week, none of which match what users understand the term to mean. Apple paid Google an estimated $1 billion annually for a system-wide seman…
A developer has found that AI agent memory systems optimized for retrieval accuracy can produce more unsafe actions than less accurate retrieval strategies, because relevance and authority are separat…
A developer building in public for 21 days discovered that every major agent memory API—including Mem0, Zep, Letta, and OpenAI's Assistants—is missing a lifecycle state field to mark facts as supersed…