RECALL — RAG Local com Privacidade
cognis-digital/recall
RAG privado, local e auditado para seus dados pessoais
Ver no GitHubMCP server que implementa RAG (Retrieval-Augmented Generation) local sobre dados pessoais com criptografia e auditoria integrada. Auto-hospedável, sem infraestrutura pesada, pronto para CI/CD e dirigido por agentes via MCP.
Instalação
npx convez-ai cognis-digital/recall1 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
Casos de uso
- Recuperação de dados pessoais com garantia de privacidade
- Integração em pipelines CI/CD para análise segura de arquivos
- Agentes de IA acessarem dados sensíveis sem expor-los
- Auditoria e conformidade de acesso a informações pessoais
Veredito

Solução robusta e bem-arquitetada para RAG privado que resolve um problema real: manter dados pessoais sob controle enquanto os torna acessíveis para agentes IA. Código maduro, testes presentes e desenho modular. Recomendado para quem precisa desse trade-off privacidade-utilidade.
README
A tradução para o português deste README ainda está na fila.
RECALL
Privacy-first local RAG over personal data — encrypted, audit-logged
Privacy / Personal — put individuals back in control of their data.
pip install cognis-recall
recall scan . # → prioritized findings in seconds
Contents
- Why recall? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why recall?
Privacy-first local RAG over personal data — encrypted, audit-logged — without standing up heavyweight infrastructure.
recall is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.
Features
- ✅ Derive Key
- ✅ Add Document
- ✅ Relevant
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-recall
recall --version
recall scan . # scan current project
recall scan . --format json # machine-readable
recall scan . --fail-on high # CI gate (non-zero exit)
Example
$ recall scan .
[HIGH ] REC-001 example finding (./src/app.py)
[MEDIUM ] REC-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
Architecture
flowchart LR
A[Input: file / dir / API] --> B[Collectors]
B --> C[Rules / Analyzers]
C --> D[Scorer]
D --> E{Reporters}
E --> F[Table]
E --> G[JSON / SARIF]
E --> H[MCP tool -. drives .-> AI agents]
Use it from any AI stack
recall is interoperable with every popular way of using AI:
- MCP server —
recall mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
recall scan . --format jsoninto any agent or LLM - LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
- CI / scripts — exit codes + SARIF for non-AI pipelines
How it compares
| Cognis recall | ollama | |
|---|---|---|
| Self-hostable, no account | ✅ | varies |
| Single command, zero config | ✅ | ⚠️ |
| JSON + SARIF for CI | ✅ | varies |
| MCP-native (AI agents) | ✅ | ❌ |
| Polyglot ports (JS/Go/Rust) | ✅ | ❌ |
| Open license | ✅ COCL | varies |
Built in the spirit of ollama/ollama, re-framed the Cognis way. Missing a credit? Open a PR.
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (recall mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
Install — every way, every platform
pip install "git+https://github.com/cognis-digital/recall.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/recall.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/recall.git" # uv
pip install cognis-recall # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/recall:latest --help # Docker
brew install cognis-digital/tap/recall # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/recall/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/recall | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
optout— Automated data-broker opt-out engine — top 50 brokers, CCPA/GDPR lettersvaultmap— Personal asset & account inventory — estate-planning-grade encryptedbreachwatch— Personal breach aggregator — HIBP + DeHashed + stealer-log triagepiicomb— Local PII discovery in your own files — SSN/CC/passport/DL/email/phone/DOBtrackblock— Family phone stalkerware audit — MVT-class iOS/Android forensicsprivacyshell— Hardened browser profile generator — Firefox / LibreWolf / Brave
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes
Contributing
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
⭐ If
recallsaved you time, star it — it genuinely helps others find it.
License
Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.