PyPI
alibaba/zvec
A lightweight, lightning-fast, in-process vector database
Apache-2.05 серп. 2026 р. · метрики 2.10.0
Усі теги
Тег каталогу
#llm-memory
Усі репозиторії публічного реєстру з цим тегом — із тем GitHub або ключових слів, які публікують їхні реєстри пакетів. Здоров'я вимірюється за тією ж версіонованою методологією, що й решта реєстру.
21 запис
PyPI
moorcheh-ai/memanto
Memory that AI Agents Love!
MIT5 вер. 2026 р. · метрики 2.10.0
PyPI · npm
cdeust/Cortex
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
MIT5 вер. 2026 р. · метрики 2.10.0
Go · PyPI
felixgeelhaar/mnemos
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
MIT16 лип. 2026 р. · метрики 2.10.0
PyPI
remete618/widemem-ai
Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
Apache-2.030 серп. 2026 р. · метрики 2.10.0
PyPI · crates.io
yantrikos/yantrikdb
Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomous consolidation, knowledge graph, ANN recall via HNSW. Embeddable Rust library with Python bindings; powers yantrikdb-server (HTTP gateway, MCP server, openraft cluster). Apache-2.0.
Apache-2.05 вер. 2026 р. · метрики 2.10.0
PyPI · npm
Mirix-AI/MIRIX
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.
Apache-2.03 серп. 2026 р. · метрики 2.10.0
npm · PyPI
qualixar/superlocalmemory
World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588
AGPL-3.019 лип. 2026 р. · метрики 2.10.0
npm
jayzeng/pi-memory
Persistent memory extension for pi with daily logs, scratchpad, and optional qmd‑powered semantic search.
MIT26 лип. 2026 р. · метрики 2.10.0
npm
rush-db/rushdb
RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.
Без ліцензії5 вер. 2026 р. · метрики 2.10.0
PyPI · npm
sachitrafa/YourMemory
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Власна ліцензія24 лип. 2026 р. · метрики 2.10.0
npm
sdsrss/claude-mem-lite
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
MIT3 серп. 2026 р. · метрики 2.10.0
npm
shakystar/memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
MIT23 лип. 2026 р. · метрики 2.10.0
PyPI
veracium-ai/Veracium
Provenance-aware memory for AI agents.
MIT2 серп. 2026 р. · метрики 2.10.0
Go
hung12ct/culi
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
MIT1 серп. 2026 р. · метрики 2.10.0
PyPI · npm
DanceNitra/inspeximus
Your agent's most expensive failure is not forgetting. It is confidently remembering the old answer. inspeximus retires a corrected fact by key, takes the correction back on command, and leaves a receipt you can verify. Long-term memory for AI agents: one zero-dependency Python file, MCP server for Claude Code, Cursor, Windsurf, Codex and Cline.
MIT29 серп. 2026 р. · метрики 2.10.0
Go
samestrin/llm-tools
High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.
MIT25 серп. 2026 р. · метрики 2.10.0
PyPI
bxw91/brainpalace
Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.
MIT18 лип. 2026 р. · метрики 2.10.0
Go
daverage/tinyMem
Local, project-scoped memory system for LLMs with evidence-based truth validation. Provides reliable long-term context via OpenAI-compatible Proxy and MCP, using Chain-of-Verification (CoVe) to eliminate hallucinations and the Ralph Loop for autonomous codebase repair.
MIT25 серп. 2026 р. · метрики 2.10.0
PyPI · npm
LycheeMem/LycheeMem
Lightweight Long-Term Memory for LLM Agents.
Apache-2.021 лип. 2026 р. · метрики 2.10.0
Go
KennFatt/manly
A fast, local CLI for turning a folder of Markdown files into a searchable, linked knowledge base.
MIT27 лип. 2026 р. · метрики 2.10.0