convez.ai
MCP ServerIntegração & APIsIntermediário
buildingjoshbetter

TrueMemory

buildingjoshbetter/TrueMemory

Memória local e automática para seus agentes de IA

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Servidor MCP que fornece memória persistente para IAs, capturando e recuperando contexto automaticamente sem dependência de nuvem. Funciona com Claude, Cursor e outras ferramentas CLI, armazenando tudo em um único arquivo SQLite local com privacidade garantida.

Instalação

$npx convez-ai buildingjoshbetter/TrueMemory

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
385
Forks
52
Acompanhando
3
Saúde
85%
Último commit
há 3 semanas
Versão
v0.7.6.2
Issues abertas
122
Contribuidores
8

Casos de uso

  • Manter contexto de longa duração em conversas com Claude ou Cursor
  • Armazenar conhecimento do projeto localmente sem exposição de dados
  • Integrar memória em fluxos de automação e agentes de IA

Veredito

MCP server sólido que resolve um problema real: IAs sem memória entre sessões. Implementação local-first é forte, mas exige setup manual e integração em fluxo existente. Útil para quem precisa de contexto persistente em desenvolvimento.

README

A tradução para o português deste README ainda está na fila.


Why TrueMemory

It finds signal in the noise. Your AI sees thousands of messages. TrueMemory figures out which ones actually matter and throws away the rest. No manual tagging, no prompt engineering. It just knows.

It gets sharper over time. It's not a static database. It's a living memory that grows with you. It resolves contradictions when you change your mind, updates stale facts, and consolidates what it knows. The longer you use it, the better it gets.

It works without you thinking about it. TrueMemory automatically captures memories from your conversations and automatically injects the right ones into your next session. You never have to store or search for anything manually. It just happens.

It's 100% local. One SQLite file on your machine. Nothing leaves your device. No cloud, no API keys needed. Your data is yours.

Without TrueMemory: "What framework are we using?" Asked for the 12th time this week. Your agent starts every session with amnesia. It doesn't know your name, your stack, or anything you told it yesterday.

With TrueMemory: Your agent already knows you use FastAPI, prefer Pydantic v2, and that your auth middleware lives in src/auth/. It remembers your corrections, your preferences, and your decisions. Across every session, forever.


How TrueMemory Compares

SystemLoCoMoLongMemEvalLocal-firstAuto-captureLicense
TrueMemory Pro93.0%92.0%✅✅AGPL-3.0
TrueMemory Base87.7%84.1%✅✅AGPL-3.0
Mem061.4%—Partial❌Apache-2.0
Supermemory65.4%—❌❌Cloud API
MemOS75.8%—✅❌Apache-2.0
ReadAgent79.5%—❌❌Research

All benchmarks independently reproducible. Scripts included in benchmarks/.


Quick Start

For Claude Code / Claude CLI / Cursor / Codex CLI / Gemini CLI

curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh

Installs everything in an isolated environment. Downloads ~1.5GB of AI models. No data leaves your machine. No sudo required.

  1. Open a terminal: Mac: Cmd + Space, type Terminal. Linux: Ctrl + Alt + T. Windows: open PowerShell.
  2. Paste the command above and press Enter.
  3. Wait 3-5 minutes for models to download.
  4. Quit your AI tool completely and reopen it (Mac: Cmd+Q).
  5. Type "Set up TrueMemory" and pick a tier.

Windows (PowerShell):

irm https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.ps1 | iex

That's it. TrueMemory remembers your conversations automatically from here.

For developers (Python library)

pip install truememory
from truememory import Memory

m = Memory()
m.add("Prefers dark mode and TypeScript", user_id="alex")
print(m.search("preferences", user_id="alex"))

Tiers

Same architecture, three tiers. All included in a single install. Switch anytime by saying "switch to Pro" or "switch to Base."

EdgeBasePro
LoCoMo89.6%92.0%93.0%
LongMemEval——92.0%
BEAM-1M——76.6% (SOTA)
Embedding model8 MB lightweight600 MB high-accuracy600 MB high-accuracy
Reranker22M params149M params149M params
HyDE search——✅ (requires LLM API key)
Runs onAny machine, CPU only4 GB+ RAM4 GB+ RAM + API key

Edge works everywhere. Base is the strongest fully-offline tier. Pro adds AI-powered query expansion for the highest scores.


Benchmarks

Tested across three major benchmarks with all systems sharing the same answer model (GPT-4.1-mini), judge (GPT-4o-mini, 3x majority vote), and scoring pipeline.

BenchmarkWhat it testsTrueMemory Pro
LoCoMo1,540 questions across 10 conversations93.0%
LongMemEval500 multi-session questions92.0%
BEAM-1M700 questions at 1M+ tokens76.6% (SOTA)
BEAM-10M200 questions at 10M tokens65.0%

Reproduce any result yourself

Every benchmark script is self-contained and runs on Modal.

All benchmarks use the same eval pipeline. Nothing is hidden. Full details: LoCoMo | LongMemEval | BEAM


Works With

Lifecycle hooks capture conversations automatically. No manual work needed. Your memories stay local in a single SQLite file.


Python API

from truememory import Memory

m = Memory()

m.add("Prefers dark mode and TypeScript", user_id="alex")
m.add("Works at Anthropic as a senior engineer", user_id="alex")

results = m.search("What are Alex's preferences?", user_id="alex")
results = m.search_deep("career history?", user_id="alex")  # multi-round, higher accuracy
MethodDescription
m.add(content, user_id)Store a memory
m.search(query, user_id)Search (6-layer pipeline + reranker)
m.search_deep(query, user_id)Multi-round agentic search
m.get(id) / m.get_all(user_id)Retrieve memories
m.update(id, content) / m.delete(id)Modify or remove
m.stats()System statistics

Full API reference →


Docs

Getting StartedInstall to first memory
Python API ReferenceFull Memory class reference
MCP Tool ReferenceAll 8 MCP tools
CLI Referencetruememory-mcp and truememory-ingest
Environment VariablesAll TRUEMEMORY_* config options
Architecture Deep Dive6-layer retrieval pipeline, encoding gate
Tier Selection GuideEdge vs Base vs Pro
DebuggingLogs, traces, common issues

FAQ

Everything lives locally in ~/.truememory/memories.db. Edge and Base tiers make zero external calls. Pro sends only your search query text to an LLM for query expansion. Your memories are never transmitted.

No. The installer uses uv to manage a sandboxed Python 3.12. Your system Python is never touched.

Context windows are expensive, slow, and empty at the start of every session. TrueMemory gives instant recall for zero tokens of context, in under 200ms.

Anonymous usage telemetry (tool calls, session counts, platform info) is on by default. We never track memory content, queries, file paths, or API keys. Opt out: export TRUEMEMORY_TELEMETRY=off


Get Started in 60 Seconds

pip install truememory

Questions? Open a Discussion. If TrueMemory saves you time, give us a ⭐


Thanks to Our Contributors


Research

TrueMemory is backed by a peer-reviewed research paper on retrieval-centered agent memory.

Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall (arXiv 2605.04897)

@article{adler2025storage,
  title   = {Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall},
  author  = {Sauron Labs},
  journal = {arXiv preprint arXiv:2605.04897},
  year    = {2025},
  url     = {https://arxiv.org/abs/2605.04897}
}

Community

If TrueMemory saves you time, give us a ⭐


License

AGPL-3.0. Free for personal and research use. Commercial use requires a separate license. Contact josh@sauronlabs.ai.


Ver o original no GitHub

Bom para

Relacionados