Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

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.

Visit GitHub
Go
984
124
7 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast pipelab-org/pipelock is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 6 – Nov 5, 2026

Stars +151 in 61 days

01020
16

Forks +25 in 61 days

012
2

Merged PRs 580 in 61 days

01020
19

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 6Sep 14Sep 22Sep 30Oct 8Oct 16Oct 24Nov 1
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Sun, Sep 6, 2026+0+013
Mon, Sep 7, 2026+0+19
Tue, Sep 8, 2026+4+119
Wed, Sep 9, 2026+1+04
Thu, Sep 10, 2026+1+28
Fri, Sep 11, 2026+0+07
Sat, Sep 12, 2026+1+015
Sun, Sep 13, 2026+0+15
Mon, Sep 14, 2026+5+012
Tue, Sep 15, 2026+16+114
Wed, Sep 16, 2026+13+18
Thu, Sep 17, 2026+3+07
Fri, Sep 18, 2026+5+014
Sat, Sep 19, 2026+2+18
Sun, Sep 20, 2026+5+18
Mon, Sep 21, 2026+3+14
Tue, Sep 22, 2026+3+010
Wed, Sep 23, 2026+3+010
Thu, Sep 24, 2026+3+011
Fri, Sep 25, 2026+1+010
Sat, Sep 26, 2026+3+112
Sun, Sep 27, 2026+5+014
Mon, Sep 28, 2026+0+010
Tue, Sep 29, 2026+0+04
Wed, Sep 30, 2026+1+018
Thu, Oct 1, 2026+4+111
Fri, Oct 2, 2026+2+014
Sat, Oct 3, 2026+1+014
Sun, Oct 4, 2026+0+014
Mon, Oct 5, 2026+1+112
Tue, Oct 6, 2026+0+010
Wed, Oct 7, 2026+1+010
Thu, Oct 8, 2026+0+114
Fri, Oct 9, 2026+0+016
Sat, Oct 10, 2026+2+116
Sun, Oct 11, 2026+0+011
Mon, Oct 12, 2026+0+012
Tue, Oct 13, 2026+4+16
Wed, Oct 14, 2026+3+01
Thu, Oct 15, 2026+1+02
Fri, Oct 16, 2026+0+18
Sat, Oct 17, 2026+5+05
Sun, Oct 18, 2026+2+18
Mon, Oct 19, 2026+1+08
Tue, Oct 20, 2026+0+010
Wed, Oct 21, 2026+13+28
Thu, Oct 22, 2026+3+15
Fri, Oct 23, 2026+5+03
Sat, Oct 24, 2026+0+013
Sun, Oct 25, 2026+0+09
Mon, Oct 26, 2026+4+010
Tue, Oct 27, 2026+2+08
Wed, Oct 28, 2026+1+03
Thu, Oct 29, 2026+5+11
Fri, Oct 30, 2026+3+09
Sat, Oct 31, 2026+2+111
Sun, Nov 1, 2026+1+118
Mon, Nov 2, 2026+1+114
Tue, Nov 3, 2026+5+010
Wed, Nov 4, 2026+1+02
Thu, Nov 5, 2026+0+00
Total+151+25580
  • 1#1 on the list
  • 7Rank that day
  • Not trending
9

    • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Go

    May 21, 2026Best #9

    #1#5#10#15#20#25
    Top 10
    May 21, 2026
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about pipelab-org/pipelock, and every badge it has earned
    1. Oct 61 post

      • A DLP rule that blocks a GitHub token on its way to GitHub is a broken rule. You find out when your agent first runs git push. The usual fixes are exempting github dot com or turning the rule off.…

        Read full on X, posted by @luckyPipewrench

        @luckyPipewrench · x.com

    2. Oct 11 post

      • Tired of coding agents that can curl your API keys straight to the open internet? Try Pipelock (luckyPipewrench/pipelock) - a Go AI agent firewall on MCP/HTTP/WebSocket egress. Blocks…

        Read full on X, posted by @sunsetsyntax

        @sunsetsyntax · x.com

    3. Sep 301 post

      • Tired of coding agents that can curl your API keys straight to the open internet? Try Pipelock (luckyPipewrench/pipelock) - a Go AI agent firewall that sits on MCP/HTTP/WebSocket egress, blocks…

        Read full on X, posted by @sunsetsyntax

        @sunsetsyntax · x.com

    4. 2 months earlier
    5. Aug 41 post

      • 🔒 An AI agent shouldn’t hold secrets and internet access in the same trust zone. It keeps keys and private context, but no direct route. Pipelock gets network access, but no agent secrets. The model…

        Read full on X, posted by @luckyPipewrench

        @luckyPipewrench · x.com

    6. 2 months earlier
    7. Jun 91 post

      • Your agent can leak a real secret in one request. It has your API keys, shell access, and a network connection. Most tools just ask you to trust a dashboard after the fact. Pipelock sits at the…

        Read full on X, posted by @luckyPipewrench

        @luckyPipewrench · x.com

    8. 7 days earlier
    9. Jun 22 posts

      • Least-privilege scoping and tool-call logs are necessary. I’d separate them from proof, though. A log produced inside the same system that approved the action is telemetry. Proof is when the action…

        Read full on X, posted by @luckyPipewrench

        @luckyPipewrench · x.com

      • 🌐🔒 PIPELOCK FIREWALL OPEN-SOURCE QUI SAUVE TES AGENTS IA DES FUITES... Les agents IA (Claude Code, Cursor, Codex, etc) ont un problème énorme : ils tournent avec des clés API, des creds et un accès…

        Read full on X, posted by @KuptoKosmos

        @KuptoKosmos · x.com

    10. Jun 11 post

      • Pipelock v2.6.0 is live 🔒 🔐 `request_policy` for operation-level egress 🪝 Hermes Agent hook bridge 🕵️ `pipelock scan` for hidden Unicode 🧾 signed demo receipts 🛡️ NSA MCP hardening + assess…

        Read full on X, posted by @luckyPipewrench

        @luckyPipewrench · x.com

    11. 11 days earlier
    12. May 211 post

      • Your coding agent has API keys in env and shell access. Pipelock sits between agent and network, scanning every HTTP/WS/MCP call. Blocks credential leaks, SSRF, injection. 618 stars. CNCF Landscape.…

        Read full on X, posted by @agentxagi

        @agentxagi · x.com

    You might also like

    Repositories close to pipelab-org/pipelock
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    denoland/clawpatrol

    Go

    Security firewall for agents

    1.1k76

    try-loopers/loopers-oss

    Go

    Firewall for the agentic era

    10718

    securetron-gh/aifw

    Python

    AI Agent Identity and Access Management and Inference Firewall

    4533

    mastyf-ai/mastyf.ai

    TypeScript

    Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.

    215

    umanitek/agent-blackbox

    Python

    Guardian Agent Blackbox: Keep your AI agents safe from being tricked or compromised

    675

    BakeLens/crust

    Go

    🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

    43935

    hashgraph-online/hol-guard

    Python

    Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

    1.1k258

    peg/rampart

    Go

    Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

    9216

    humanbound/humanbound-firewall

    Python

    Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

    566