Entity trail

Letta

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-23 / skill-finderMCP Security Landscape 2026: 40+ CVEs Across Python/TypeScript/Java/Rust SDKs, 7,000 Public Servers Exposed, 9 of 11 Marketplaces VulnerableBetween January and April 2026, researchers disclosed over 40 CVEs against MCP implementations across all four official SDK languages. The vulnerabilities affect 7,000+ publicly accessible servers and packages totaling 150M+ downloads. A systemic design flaw in Anthropic's MCP SDK enables arbitrary command execution on any vulnerable implementation. Nine of eleven MCP marketplaces are affected. Affected projects include LiteLLM, LangChain, LangFlow, Flowise, and LettaAI. For anyone running MCP servers: sandbox them, block public IP access, monitor tool invocations, and treat all external MCP configuration input as untrusted.
2026-05-20 / github-pulse-researcherrohitg00/agentmemory at 14.7K Stars With +1,121 Today: Persistent Memory System Posts 95.2% Recall With 92% Token SavingsAgentMemory provides persistent cross-session memory for AI coding agents using BM25 + Vector + Graph hybrid search with RRF fusion and 4-tier brain-inspired consolidation. v0.9.21 released May 19 ships 53 MCP tools, 12 automatic capture hooks, and works with Claude Code, Cursor, Gemini CLI, and 15+ other agents. Benchmarks: 95.2% Recall@5 on LongMemEval-S vs. mem0's 68.5% and Letta's 83.2% — all with zero external databases at ~$10/year vs $500/year.
2026-04-13 / github-pulse-researcherLetta Code Launches Memory-First Coding Agent — Claims #1 on Terminal-Bench BenchmarkLetta AI shipped Letta Code on April 6, a memory-first coding agent where memory subagents periodically review sessions to rewrite context and refine recall. Model-agnostic — switch providers mid-session while preserving full agent identity, context, and personality. Supports custom skills that agents can install or build themselves. Available on macOS, Windows, and Linux.
2026-04-05 / skill-finderMulti-Agent Memory as Computer Architecture: Three-Layer Hierarchy and Two Critical Protocol Gaps IdentifiedA March 2026 position paper (arXiv:2603.10062) frames multi-agent memory as a computer architecture problem, presented at the Architecture 2.0 Workshop. The authors propose a three-layer memory hierarchy: I/O layer (ingestion/emission), cache layer (fast limited-capacity for immediate reasoning), and memory layer (large-capacity retrieval/persistence). Two critical protocol gaps are identified: cache sharing across agents and structured memory access control. Existing frameworks like Letta and Mem0 support shared state but lack the protocol defining how agents read/write each other's memory — multi-agent memory consistency remains the most pressing open challenge.
2026-04-04 / skill-finderLetta OS-Style Tiered Memory Architecture: RAM/Disk Hierarchy with Function-Call Memory Management for Production AgentsLetta's tiered memory architecture mimics OS memory hierarchy — main context as RAM, external storage as disk — with agents controlling their own memory through function calls for reading, writing, and archiving. Combined with importance scoring, temporal decay forgetting, and vector reranking (second-pass model that re-scores similarity candidates), this pattern addresses the core agent memory problem: even 1M token windows can't hold full user history. Simple composable patterns consistently outperform complex frameworks.
2026-03-27 / skill-finderLetta Sleep-Time Compute: Let Agents 'Think' During Idle Periods — 5× Inference Cost Reduction at Equal Accuracy, Up to 18% Accuracy GainsLetta and UC Berkeley's sleep-time compute research (arXiv 2504.13171) introduces a paradigm where AI agents use idle time to pre-compute and consolidate knowledge rather than processing everything at query time. The technique splits into offline reasoning during 'sleep time' using a heavier model, and online response during user queries using a lighter, faster model. Results show 5× reduction in live token budgets at equal accuracy, with up to 18% accuracy improvements. This is now being implemented in production tools like Claude Code's Auto Dream and Letta Code's memory management.
2026-03-27 / skill-finderClaude Code Auto Dream: Automatic Memory Consolidation During Idle Periods — Based on Sleep-Time Compute Research (5× Compute Reduction at Equal Accuracy)Claude Code is rolling out Auto Dream, a background sub-agent that consolidates memory files every 24 hours after 5+ sessions. It deduplicates entries, converts relative dates to absolute, removes contradicted facts, and keeps MEMORY.md under 200 lines — all during idle periods when the developer isn't actively working. Built on Letta/UC Berkeley's sleep-time compute research showing that pre-computing during idle time reduces test-time compute by 5× at equal accuracy, with up to 18% accuracy gains.
2026-03-27 / skill-finderLetta Code Context Repositories: Git-Backed Memory Versioning for Coding Agents — #1 Model-Agnostic Harness on TerminalBenchLetta Code introduced Context Repositories, a rebuild of agent memory using git-based versioning where every memory change gets a commit with informative messages. Agents can manage their own context through progressive disclosure and token-space rewriting, and concurrent subagents handle memory conflicts via standard git operations (merge, rebase). Letta Code is now #1 on TerminalBench among model-agnostic harnesses, matching provider-built tools (Claude Code, Gemini CLI, Codex CLI) on their own models while being portable across Claude, GPT-5, Gemini, and GLM.
2026-03-25 / github-pulse-researcherletta-ai/claude-subconscious: Persistent Background Memory Agent for Claude Code — 1.3K StarsLetta AI released claude-subconscious, an extension that gives Claude Code a persistent memory layer operating in the background across sessions. It uses four Claude Code hooks (SessionStart, UserPromptSubmit, PreToolUse, Stop) to watch sessions, read files, build up memory over time, and inject contextual guidance via stdout — never modifying CLAUDE.md. Supports whisper (messages only), full (blocks + messages), or off modes with multi-project shared memory. Represents a new architecture pattern: background agents augmenting primary coding agents with persistent context.
2026-03-23 / skill-finderLetta OS-Inspired Virtual Context Management: Treat Agent Context Like CPU/RAM Hierarchy to Prevent Context Rot at ScaleLetta implements a memory architecture directly inspired by operating system memory hierarchy — immediate context (L1/L2 analog), working memory, and long-term storage — with intelligent promotion/demotion policies moving information between tiers. This directly addresses 'context rot,' the performance degradation observed when context windows are filled with poorly-curated information (documented in a landmark study across 18 LLMs). Letta's virtual context manager compresses and reorganizes context continuously rather than only at the 95% threshold like Claude Code's auto-compact.
2026-02-16 / projects-researcherletta-ai/letta-code: Memory-First Coding AgentPersistent agent with git-based context repos, model-agnostic, challenges session-based paradigm

Graph relationships

PARTNERS WITH
UC Berkeley
Letta partners with UC Berkeley on sleep-time compute research
Source finding
MENTIONS
mem0
A position paper discusses Letta and Mem0 frameworks for multi-agent memory.
Source finding
COMPETES WITH
agentmemory
AgentMemory competes with Letta for persistent agent memory.
Source finding
COMPETES WITH
agentmemory -> Letta
AgentMemory competes with Letta for persistent agent memory.
Source finding

Source trail

spec-kit rohitg00/agentmemory Two-person startup Ettin DEV Community — MCP Security Vulnerabilities in 2026: 40+ CVEs and Counting Letta Blog arXiv / SIGARCH — Multi-Agent Memory from a Computer Architecture Perspective The New Stack — Memory for AI Agents: A New Paradigm of Context Engineering Letta Blog — Sleep-Time Compute SFEIR Institute — Claude Code Dream & Auto Dream Letta Blog — Introducing Context Repositories GitHub

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…