- 记忆梦境引擎 · AI 的睡眠系统 @savantcat/memory-dream-engine零 LLM 事实提取 + 三维信号评分 + 艾宾浩斯衰减 + 五阶段梦境流水线与内容发芽检测，纯计算零依赖4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Devin Memory @icaro0310/devin-memoryAnti-poisoning memory for agents: provenance, conflicts, quarantine gate.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- ContextLib @willykeenan/agentbrain-contextlibA project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- heropen — AI Agent Memory @heropen/heropenPersistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Edith Second Brain @rchari1/edith-second-brainClaude distils its past sessions into linked Markdown notes on disk and searches them later.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- nanomem @ombansod2/nanomemMemory that knows when a remembered fact has been replaced, not just when it was written.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- CueMap @cuemap-dev/cuemap-mcpLocal memory and context retrieval for AI agents through CueMap.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Engram @devinmlowe/engramCognitive memory for coding agents: hybrid recall, remember/forget, knowledge graph, nightly dreams.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agentos @officialtanishsharma/agentosLocal-first persistent memory MCP server for AI coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Engraphy @devon-clarkk/engraphySelf-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- AI Pensieve MCP @as-xs/ai-pensieve-mcpSearch and cross-reference local AI chat history with read-only tools and source citations.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Vibo @vnbochkarev-netizen/vibo-mcpPersistent memory for AI agents: L1/L2/L3, web compression, threads.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tether @sidyellur/tetherLocal-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Cognitive Substrate @jaysonaionline/cognitive-substrate28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- CP Memory @cjhuochai/cp-memoryLocal-first, governable long-term memory for AI coding agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- memdsl @liyuan1992/memdslReview-gated declarative long-term memory with bounded read-only MCP access.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- rawmem @liyuan1992/rawmemRead-only MCP access to a local append-only evidence ledger for AI agent sessions.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- loci @3m1ry33t/lociScoped memory for coding agents: picks the right project, answers in scope, or abstains.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- CogSession @premanand8800/cogsessionSession memory for AI coding agents: records decisions and dead ends, flags what went stale.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Homestead Memory @fuckbigtech-ai/homestead-memoryTamper-evident record of what your AI agent did, plus local-first verifiable memory.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- ContextDB Memory @mikhailbovt/contextdb-memoryLocal-first durable AI memory with policy-bound recall and a typed project graph.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- Claude Handoff @vasilispapg/claude-handoffSession handoff for Claude Code: list sessions and build handoff docs another agent continues from.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- YodMCP @anamized/yodmcpAutonomous MCP Agent OS: multi-graph memory, Tasks, Skills, A2A, attestation, OpenTelemetry.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- LocalKeep @zuneracodes/localkeepLocal chronological memory banks you control; Claude recalls them via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
