Todas las etiquetas
Etiqueta del catálogo

#agent-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.

62 registros
Con la etiqueta «agent-memory»Ordenado por índice de salud
Go
64Moderadoíndice 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 1.13.0
npm
64Moderadoíndice de salud
roackb2/heddle
An open-source terminal coding agent runtime and CLI for real project work.
TypeScript★ 17↓ 1870/mes20 jul 2026
MIT20 jul 2026 · métricas 1.13.0
npm
63Moderadoíndice de salud
avids2/memorix
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
TypeScript★ 546↓ 2444/mes13 jul 2026
Apache-2.013 jul 2026 · métricas 1.13.0
Go
63Moderadoíndice de salud
rekal-dev/rekal-cli
Git-anchored decentralised intent(conversation) ledger for teams who build with AI
Go · Python★ 521 jul 2026
Apache-2.021 jul 2026 · métricas 1.13.0
npm
63Moderadoíndice de salud
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.
TypeScript★ 12↓ 3646/mes23 jul 2026
MIT23 jul 2026 · métricas 1.13.0
crates.io · PyPI
63Moderadoíndice de salud
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). AGPL.
Rust★ 39↓ 4983/mes14 jul 2026
AGPL-3.014 jul 2026 · métricas 1.13.0
PyPI · npm
62Moderadoíndice de salud
ccf/agentcairn
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
Python★ 18↓ 3609/mes16 jul 2026
Apache-2.016 jul 2026 · métricas 1.13.0
PyPI
61Moderadoíndice de salud
0Mattias/bettermemory
the trust layer for agent memory
Python★ 0↓ 3619/mes20 jul 2026
MIT20 jul 2026 · métricas 1.13.0
PyPI
61Moderadoíndice de salud
intertwine/observational-memory
Local-first shared memory for Claude Code, Codex, OpenCode, Kimi, Grok, Cowork, and Hermes, with bounded observation and searchable Markdown context.
Python★ 1719 jul 2026
MIT19 jul 2026 · métricas 1.13.0
Go
60Moderadoíndice de salud
rekal-dev/cli
Git-anchored decentralised intent(conversation) ledger for teams who build with AI
Go · Python★ 417 jul 2026
Apache-2.017 jul 2026 · métricas 1.13.0
npm · Go
60Moderadoíndice de salud
valtors/relay
MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.
Go · JavaScript★ 9↓ 1536/mes15 jul 2026
MIT15 jul 2026 · métricas 1.13.0
npm
59Moderadoíndice de salud
Medhovarsh/forkmind
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
JavaScript★ 2↓ 2178/mes24 jul 2026
MIT24 jul 2026 · métricas 1.13.0
npm
59Moderadoíndice de salud
davesheffer/hunch
Local-first engineering memory for AI coding: a git-native graph of decisions, bugs, and invariants, exposed to Claude Code via MCP.
TypeScript · HTML · JavaScript★ 0↓ 11.3K/mes19 jul 2026
Apache-2.019 jul 2026 · métricas 1.13.0
npm
58Moderadoíndice de salud
iHow1/ihow-memory-core
Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.
JavaScript · TypeScript★ 1↓ 3284/mes19 jul 2026
Apache-2.019 jul 2026 · métricas 1.13.0
npm
57Moderadoíndice de salud
samfoy/pi-memory
Persistent memory for pi — learns corrections, preferences, and patterns from sessions
TypeScript★ 81↓ 2383/mes17 jul 2026
MIT17 jul 2026 · métricas 1.13.0
npm
57Moderadoíndice de salud
syntaxPriest/openvisio-oss
El repositorio no publica descripción.
TypeScript★ 10↓ 2951/mes23 jul 2026
MIT23 jul 2026 · métricas 1.13.0
PyPI
56Moderadoíndice de salud
CaspianG/wavemind
Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.
Python★ 5↓ 6194/mes14 jul 2026
MIT14 jul 2026 · métricas 1.13.0
npm
56Moderadoíndice de salud
Goldentrii/AgentRecall-MCP
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
JavaScript · TypeScript · HTML★ 30917 jul 2026
MIT17 jul 2026 · métricas 1.13.0
Go
55Moderadoíndice de salud
EclipseElips/recoil
Memory for AI coding agents — remembers what goes wrong, reminds you before it happens again. One Go binary, no embeddings.
Go★ 1617 jul 2026
MIT17 jul 2026 · métricas 1.13.0
PyPI
55Moderadoíndice de salud
mrsalty/slowave
A living local memory layer for your AI tools.
Python★ 1↓ 4894/mes14 jul 2026
Licencia propia14 jul 2026 · métricas 1.13.0
—
55Moderadoíndice de salud
syncable-dev/memtrace-public
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.
Python★ 43519 jul 2026
Licencia propia19 jul 2026 · métricas 1.13.0
Go
55Moderadoíndice de salud
witwave-ai/witself
Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.
Go★ 0↓ 0/mes14 jul 2026
Licencia propia14 jul 2026 · métricas 1.13.0
npm
50Moderadoíndice de salud
jonny981/loops
A small, nestable agent-loop job primitive: loop(body→until→review) composed with dag, pluggable engines, agent-judge gates, budget + run records. TypeScript.
TypeScript★ 11↓ 2383/mes23 jul 2026
MIT23 jul 2026 · métricas 1.13.0
npm
49En riesgoíndice de salud
ruvnet/agentdb
Vector memory that gets smarter every time your agent uses it.
TypeScript · HTML · JavaScript★ 80↓ 649.1K/mes23 jul 2026
MIT23 jul 2026 · métricas 1.13.0
PyPI
48En riesgoíndice de salud
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.
Python★ 2↓ 5690/mes18 jul 2026
MIT18 jul 2026 · métricas 1.13.0
npm
47En riesgoíndice de salud
sabaiway/agent-workflow
Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin, and more. Monorepo: memory substrate, the kit (composition root), CLI bridges, and the engine.
JavaScript★ 0↓ 16.9K/mes22 jul 2026
MIT22 jul 2026 · métricas 1.13.0
Go
45En riesgoíndice de salud
Dieg0Code/nem
Your agent forgets; nem doesn't. mnemonics encodes a session's decisions, edge-cases and facts into immutable, recallable structure — versioning agent context the way git versions code, shared across Claude & Codex.
Go★ 117 jul 2026
MIT17 jul 2026 · métricas 1.13.0
PyPI · npm
45En riesgoíndice de salud
LycheeMem/LycheeMem
Lightweight Long-Term Memory for LLM Agents.
Python · TypeScript★ 1152↓ 78/mes21 jul 2026
Apache-2.021 jul 2026 · métricas 1.13.0
npm
44En riesgoíndice de salud
holgerreppert/opencode-fractal-memory
A fractal memory plugin and mcp server for opencode.
TypeScript · JavaScript★ 1↓ 3665/mes17 jul 2026
MIT17 jul 2026 · métricas 1.13.0
npm
44En riesgoíndice de salud
misunders2d/pi-experiences
Pi package for reviewed behavioral experience patterns separate from skills and memory
TypeScript · JavaScript★ 2↓ 3731/mes16 jul 2026
MIT16 jul 2026 · métricas 1.13.0