Todas las etiquetas
Etiqueta del catálogo

#long-term-memory

Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.

22 registros
Con la etiqueta «long-term-memory»Ordenado por índice de salud
npm · PyPI
98Excepcionalíndice de salud
mem0ai/mem0
Universal memory layer for AI Agents
Python · TypeScript★ 62.5K↓ 379.8K/mes4 ago 2026
Apache-2.04 ago 2026 · métricas 2.10.0
PyPI
95Excepcionalíndice de salud
MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
TypeScript · Python★ 11K28 ago 2026
Apache-2.028 ago 2026 · métricas 2.10.0
PyPI · npm
94Excepcionalíndice de salud
plastic-labs/honcho
Memory library for building stateful agents
Python★ 6456↓ 1336/mes5 ago 2026
AGPL-3.05 ago 2026 · métricas 2.10.0
PyPI
92Excelenteíndice de salud
moorcheh-ai/memanto
Memory that AI Agents Love!
Python · HTML★ 1859↓ 4158/mes5 sept 2026
MIT5 sept 2026 · métricas 2.10.0
PyPI · npm · crates.io
92Excelenteíndice de salud
vectorize-io/hindsight
Hindsight: Agent Memory That Learns
Python · TypeScript★ 19.1K↓ 81.9K/mes5 ago 2026
MIT5 ago 2026 · métricas 2.10.0
npm · PyPI
91Excelenteíndice de salud
joshuaswarren/remnic
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
TypeScript★ 176↓ 203.7K/mes22 ago 2026
MIT22 ago 2026 · métricas 2.10.0
PyPI · npm
89Excelenteíndice de salud
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.
Python★ 71↓ 2447/mes5 sept 2026
MIT5 sept 2026 · métricas 2.10.0
npm
89Excelenteíndice de salud
thedotmack/claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
JavaScript · TypeScript★ 89.6K↓ 63.5K/mes4 ago 2026
Apache-2.04 ago 2026 · métricas 2.10.0
PyPI
89Excelenteíndice de salud
zilliztech/memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
Python · Shell★ 2250↓ 102.3K/mes18 jul 2026
MIT18 jul 2026 · métricas 2.10.0
PyPI
83Excelenteíndice de salud
skynetcmd/m3-memory
Local-first Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable
Python★ 19↓ 8178/mes9 ago 2026
Apache-2.09 ago 2026 · métricas 2.10.0
PyPI
81Excelenteíndice de salud
remete618/widemem-ai
Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
Python★ 48↓ 41/mes30 ago 2026
Apache-2.030 ago 2026 · métricas 2.10.0
Go
73Buenoíndice de salud
Dakera-AI/dakera-go
Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.
Go★ 319 jul 2026
Licencia propia19 jul 2026 · métricas 2.10.0
npm
71Buenoíndice de salud
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.
JavaScript★ 49↓ 8084/mes3 ago 2026
MIT3 ago 2026 · métricas 2.10.0
PyPI · npm
69Buenoíndice de salud
CaspianG/wavemind
Adaptive memory for agents: durable local-first state, scoped recall, reinforcement, forgetting, consolidation, and reproducible benchmarks.
Python★ 7↓ 1677/mes22 ago 2026
MIT22 ago 2026 · métricas 2.10.0
npm · Go
63Moderadoíndice de salud
EverMind-AI/EverMe
Open-source CLI and Agent plugin suite for EverMe — cross-device, cross-Agent personal memory for AI Agents.
Go · JavaScript★ 40↓ 3237/mes27 jul 2026
Apache-2.027 jul 2026 · métricas 2.10.0
Go
63Moderadoíndice de salud
achetronic/magec
Multi-agent AI platform with voice and text control. Visual workflows, web interface, and chat integrations (Telegram, Discord, Slack). Long-term memory, any LLM backend, extensible via MCP tools.
Go · Vue★ 10217 jul 2026
Apache-2.017 jul 2026 · métricas 2.10.0
PyPI
63Moderadoíndice de salud
veracium-ai/Veracium
Provenance-aware memory for AI agents.
Python★ 5↓ 2657/mes2 ago 2026
MIT2 ago 2026 · métricas 2.10.0
PyPI · npm
57Moderadoíndice de salud
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.
Python★ 6↓ 9803/mes29 ago 2026
MIT29 ago 2026 · métricas 2.10.0
npm
57Moderadoíndice de salud
bacnh85/pi-extensions
Pi coding agent extension packages — tools, skills, and integrations.
TypeScript★ 9↓ 7997/mes29 ago 2026
Sin licencia29 ago 2026 · métricas 2.10.0
npm
45Débilíndice de salud
best-linux-code/opencode-hindsight-plus
Hindsight memory plugin for OpenCode with Claude Code-aligned per-turn auto-recall
TypeScript★ 0↓ 2121/mes26 jul 2026
MIT26 jul 2026 · métricas 2.10.0
PyPI
45Débilíndice de salud
teleport-computer/memgarden
记忆的编辑判断:什么值得记、归哪个桶、几张卡、什么时候该整理。不调模型、不碰存储。
Python★ 0↓ 2907/mes6 sept 2026
Apache-2.06 sept 2026 · métricas 2.10.0
npm · Maven
38Débilíndice de salud
zhangsen540445123/claw-manager
El repositorio no publica descripción.
TypeScript · Java★ 0↓ 9208/mes25 jul 2026
Sin licencia25 jul 2026 · métricas 2.10.0