dlp repositories
Trending repositories tagged dlp, ranked by trending score. Updated daily.
-
1
pipelab-org/pipelock
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub · Go · 1,009 stars · 113 forks · +7 stars in 24 hours · Trending score 1.63
-
2
sn4k3/UVtools
MSLA/DLP, file analysis, calibration, repair, conversion and manipulation
GitHub · C# · 1,659 stars · 147 forks · +3 stars in 24 hours · Trending score 1.35
-
3
blitzcrieg1/agentmetry
Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail in the SIEM you already run.
GitHub · Python · 47 stars · 5 forks · +1 stars in 24 hours · Trending score 0.77
-
4
forgd-ai/forgd-verdict
Data loss prevention for Claude: finds secrets and personal data in prompts and responses, blocks prompts through inference hooks, and scans Compliance API history. Self-hosted on Azure, AWS or Google Cloud.
GitHub · Python · 6 stars · 2 forks · +1 stars in 24 hours · Trending score 0.55
-
5
Mcpgate-de/maisecrets
Keeps secrets and personal data out of Claude Code and Codex. Local, deterministic, no model to download: Python's standard library only.
GitHub · Python · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.32
-
6
pipelab-org/agent-egress-bench
Open Apache-2.0 corpus, runner, scoring, and result-verification contracts for measuring AI-agent egress controls. A PipeLab open project.
GitHub · Go · 24 stars · 2 forks · 0 stars in 24 hours · Trending score 0.23
-
7
awslabs/ferret-scan
Find and redact sensitive data before it leaks — a fast, offline CLI and Go library that detects PII, secrets, and credentials in files and streams, scores them with context-aware confidence, and redacts them format-preserving. Nothing leaves your host.
GitHub · Go · 104 stars · 13 forks · 0 stars in 24 hours · Trending score 0.20
-
8
flare-collection/flare-redact
Keep secrets and PII out of logs, Sentry, LLM prompts and commits. Reads values, not field names. Zero dependencies.
GitHub · TypeScript · 52 stars · 2 forks · 0 stars in 24 hours · Trending score 0.19
-
9
yurivenancio30/llm-dlp
Local proxy that masks sensitive data between you and the LLM (Claude Code): the API only sees pseudonyms
GitHub · Go · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.14
-
10
node9-ai/node9-proxy
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
GitHub · TypeScript · 225 stars · 21 forks · 0 stars in 24 hours · Trending score 0.10
-
11
diderisoft/bot-bottle
Run AI coding agents with broad permissions in an isolated sandbox: credentials stay outside, and everything that leaves is checked.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
12
openmasq/openmasq
Privacy-first desktop chat for multiple LLMs: sensitive values are redacted on-device before any network call, and restored in the reply. Your own keys, a local model, or a CLI subscription. The engine ships on npm as @openmasq/redact.
GitHub · TypeScript · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08
-
13
censgate/redact
Fast Rust engine for detecting and redacting PII and secrets — in prompts, code, and databases. OpenAI-compatible gateway, Postgres scanner, CLI, and WASM. 32× Presidio. Apache-2.0.
GitHub · Rust · 23 stars · 3 forks · 0 stars in 24 hours · Trending score 0.07
-
14
Milvago-AI/milvago-server
Open source Shadow AI governance: discover the AI platforms your organization uses, see what leaves the browser, and mask it before it does. Server and console, AGPL-3.0.
GitHub · Go · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.06
-
15
Brain0-ai/brain0
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
GitHub · Rust · 278 stars · 11 forks · −11 stars in 24 hours · Trending score 0.03
-
16
gitleaks/gitleaks
Find secrets with Gitleaks 🔑
GitHub · Go · 30,486 stars · 2,323 forks · 0 stars in 24 hours · Trending score 0.00
-
17
jnMetaCode/shellward
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」(网安法·PIPL·等保2.0·数据出境·AI标识),并给出境内模型替代建议;可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源
GitHub · TypeScript · 138 stars · 24 forks · 0 stars in 24 hours · Trending score 0.00
-
18
Ishannaik/agent-sweep
Find and redact secrets in AI coding agent histories (Claude Code, and more).
GitHub · Python · 88 stars · 52 forks · 0 stars in 24 hours · Trending score 0.00
-
19
DavidCarliez/cover
Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.
GitHub · Go · 58 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00
-
20
strac-io/strac-mcp-dlp
MCP server for Strac DLP — detect and redact PII, PHI, PCI and secrets before an AI agent sees them.
GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
21
fregie/tokenhush
Local base-URL gateway that redacts secrets and PII before they leave your machine
GitHub · Go · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
22
Avagodo/wdfilter-research
Reverse engineering and Reconstruction of Microsoft Defender's WdFilter.sys for Windows minifilter callbacks, registry monitoring, process tracking, DLP, and hardening.
GitHub · C · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
23
oleg-vdv/AI-Gateway
On-prem LLM compliance gateway: detects PII and secrets in prompts, reversibly masks them before they reach ChatGPT/Claude/Gemini, restores them in the response, with a tamper-evident audit log
GitHub · Python · 11 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
24
RitualDev-Lab/AgentShield
Enterprise runtime security firewall and governance layer for autonomous AI agents, LLMs, and MCP tools with real-time DLP, zero-trust gating, and audit logging.
GitHub · TypeScript · 5 stars · 5 forks · Trending score 0.10