llm-memory repositories
Trending repositories tagged llm-memory, ranked by trending score. Updated daily.
-
1
vshulcz/deja-vu
Claude Code, Codex & Cursor memory — local MCP memory, session history search & coding agent handoff.
GitHub · Go · 1,637 stars · 184 forks · +24 stars in 24 hours · Trending score 2.68
-
2
omdsh-dev/dsh-mnemon
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
GitHub · TypeScript · 1,041 stars · 73 forks · +12 stars in 24 hours · Trending score 2.57
-
3
alibaba/zvec
A lightweight, lightning-fast, in-process vector database
GitHub · C++ · 16,272 stars · 1,029 forks · +8 stars in 24 hours · Trending score 2.10
-
4
electricsheephq/lcm-x
Lossless memory for Hermes Agent: every turn kept in a local store, not compacted away, and searchable by your agent.
GitHub · Python · 171 stars · 22 forks · +7 stars in 24 hours · Trending score 1.91
-
5
mnemon-dev/mnemon
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
GitHub · Go · 724 stars · 83 forks · +5 stars in 24 hours · Trending score 1.67
-
6
caura-ai/caura
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
GitHub · Python · 567 stars · 110 forks · +3 stars in 24 hours · Trending score 1.23
-
7
Filippo-Venturini/ctxvault
Local-first memory for AI agents: semantic, procedural and episodic vaults you compose, control and query. CLI, MCP, HTTP and Python.
GitHub · Python · 69 stars · 22 forks · +1 stars in 24 hours · Trending score 1.16
-
8
SLEEPYBQ/MemoSync
Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex, Pi and OpenCode.
GitHub · TypeScript · 312 stars · 16 forks · 0 stars in 24 hours · Trending score 1.13
-
9
TeleAI-UAGI/Awesome-Agent-Memory
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
GitHub · Python · 714 stars · 176 forks · +1 stars in 24 hours · Trending score 1.09
-
10
Riley-Coyote/mnemos-mcp
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
GitHub · Python · 173 stars · 22 forks · +1 stars in 24 hours · Trending score 1.05
-
11
qingsongcui/ContextCore
Senrelay · 续境 — Local-first macOS multi-Agent conversation relay, source-linked persistent memory, and unified host configuration workbench.
GitHub · Python · 101 stars · 0 forks · 0 stars in 24 hours · Trending score 1.01
-
12
tinqiao-oss/engramory
Agent 通用长期记忆层:Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档,文档以链接形式列在限长索引中,索引随会话自动注入。DeepSeek Harness(dsh)有专用插件 dsh-engramory。
GitHub · JavaScript · 208 stars · 12 forks · +2 stars in 24 hours · Trending score 1.00
-
13
aru-labs/lossless-memory
Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything.
GitHub · Python · 172 stars · 16 forks · 0 stars in 24 hours · Trending score 1.00
-
14
hyperb1iss/sibyl
Cross-agent memory for AI coding tools: one self-hostable knowledge graph shared by Claude Code, Codex, OpenCode, Cursor, and the agents you build.
GitHub · Python · 70 stars · 10 forks · +2 stars in 24 hours · Trending score 0.91
-
15
ZIZKA-AI-SL/ZizkaDB
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
GitHub · Python · 164 stars · 43 forks · +2 stars in 24 hours · Trending score 0.81
-
16
krapcys1-maker/adaptive-agent-memory-research
Experience memory for LLM agents that act, tested one rung at a time against token-matched placebo controls. Latest published lab result (ALFWORLD-LADDER-R4-V5B, 201 units): mismatched_type vs placebo +1.5 points (95% CI −6.7 to +9.7, equivalent); retrieved_task vs placebo +16.9 points (95% CI +5.3 to +28.5, positive).
GitHub · Python · 10 stars · 5 forks · +1 stars in 24 hours · Trending score 0.79
-
17
Andsu-dev/runelay
runelay: open-source, self-hosted MCP gateway. One MCP endpoint for every account, skill and memory your agents use (Claude Code, Codex, Cursor).
GitHub · TypeScript · 25 stars · 1 forks · +3 stars in 24 hours · Trending score 0.73
-
18
kitfunso/hippo-memory
One memory for every agent you'll ever use. Hippo writes what you teach a coding agent into a store in your repo, and your other agents read that same store.
GitHub · TypeScript · 795 stars · 47 forks · +1 stars in 24 hours · Trending score 0.69
-
19
Kronic90/Mimirs-Memory-Hub
Local AI companion with persistent, human-like memory that remembers you across sessions. Works with Ollama, GGUF/llama.cpp, LM Studio & any OpenAI-compatible API; imports SillyTavern cards. Windows portable zip, no install.
GitHub · Python · 38 stars · 3 forks · 0 stars in 24 hours · Trending score 0.69
-
20
mnemoverse/awesome-agent-memory
A curated list of memory systems, frameworks, benchmarks, and research for AI agents.
GitHub · 68 stars · 80 forks · 0 stars in 24 hours · Trending score 0.68
-
21
tenurehq/tenure
Persistent, governed memory for chat clients, IDEs, & agents. Share memory across clients without losing scope, provenance, or auditability.
GitHub · TypeScript · 31 stars · 5 forks · −1 stars in 24 hours · Trending score 0.66
-
22
clearyss/WeLoom
基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成,将聊天记录转化为高拟真的数字分身。
GitHub · Python · 41 stars · 1 forks · 0 stars in 24 hours · Trending score 0.61
-
23
MrPeppersDev/agent-infrastructure-landscape
AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, agent frameworks, runtimes, vector stores, knowledge graphs, MCP servers, benchmarks. Searchable with typed edges, lineages, citations.
GitHub · HTML · 8 stars · 0 forks · +1 stars in 24 hours · Trending score 0.56
-
24
DanceNitra/inspeximus
The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.
GitHub · Python · 8 stars · 1 forks · +1 stars in 24 hours · Trending score 0.55