HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
91.
▲
Show HN: Pandora: let ChatGPT edit files, run commands and manage Docker
github.com/dave1010
discuss
3 years ago
dave1010uk
4 points
92.
▲
Show HN: Cyber-forensics for public PCs using ML to detect hate speech, threats
discuss
8 years ago
allisterb
4 points
93.
▲
Show HN: Railyard – open and secure runtime for Claude Code
5 comments
3 months ago
LunarFrost88
3 points
94.
▲
Show HN: Nucleus – enforced permission envelopes for AI agents (Firecracker)
github.com/coproduct-opensource
3 comments
5 months ago
difc
3 points
95.
▲
Ask HN: Is Docker to blame for recent security breaches?
3 comments
6 years ago
figassis
3 points
96.
▲
Show HN: AgentVM – Safe, Sandboxed Linux VM for OpenClaw and AI Agents
agentvm.deepclause.ai
2 comments
5 months ago
phunterlau
3 points
97.
▲
Show HN: The Rouge is my attempt at an AI product factory
github.com/gregario
1 comment
2 months ago
gr3gario
3 points
98.
▲
Show HN: Axon – Let coding agents develop their own framework on Kubernetes
github.com/axon-core
1 comment
4 months ago
gjkim042
3 points
99.
▲
Show HN: `seven up` is `vagrant up` made of sprite (Fly.io) for safe vibe-coding
github.com/1to10partners
1 comment
5 months ago
mtremsal
3 points
100.
▲
Show HN: Research-Backed Multi-Agent System for Autonomous Development
github.com/asklokesh
1 comment
5 months ago
slogansand
3 points
101.
▲
Show HN: Cco – a sandbox for Claude Code so you can YOLO made safe(ish)ly
github.com/nikvdp
1 comment
a year ago
nikvdp
3 points
102.
▲
Ask HN: How to convince my company to avoid dark patterns?
1 comment
6 years ago
gingerlime
3 points
103.
▲
Show HN: DollhouseMCP 2.0, open-source MCP composable AI building blocks
dollhousemcp.com
discuss
2 months ago
mickdarling
3 points
104.
▲
CVE-2026-33691: OWASP CRS whitespace padding bypass vulnerability
discuss
3 months ago
relunsec
3 points
105.
▲
Show HN: First-token-only flaw in Claude Code permissions (triage bot too)
spitfirecowboy.com
discuss
3 months ago
Apylon777
3 points
106.
▲
Show HN: Golf Scanner – OSS tool to find and audit every MCP server
github.com/golf-mcp
discuss
4 months ago
antonig
3 points
107.
▲
I built an AI browser with prompt-injection defense at 16 on an i5 with 8GB RAM
discuss
4 months ago
latestinssan
3 points
108.
▲
Show HN: I built a sandboxed VM for letting AI agents go wild without risks
discuss
5 months ago
pancakeInDev
3 points
109.
▲
Show HN: Mother May I? – Auto-approve safe Bash commands in Claude Code
github.com/dgerlanc
discuss
5 months ago
dgerlanc
3 points
110.
▲
Show HN: An SDK for building custom coding agents with tools and sub-agents
discuss
a year ago
chw9e
3 points
111.
▲
Ask HN: Using GPT as a logic circuit instead of a text generator – Anyone tried?
4 comments
a year ago
GENIXUS
2 points
112.
▲
MCP servers mass-forked and republished – supply-chain attack vector
2 comments
3 months ago
ultrafox42
2 points
113.
▲
Hawkeye – open-source flight recorder
2 comments
3 months ago
mklamine
2 points
114.
▲
Show HN: ClawShield – Open-source security proxy for AI agents (Go, eBPF)
github.com/SleuthCo
2 comments
4 months ago
sleuthco
2 points
115.
▲
Show HN: AI-runtime-guard – Policy enforcement layer for MCP AI agents
github.com/jimmyracheta
2 comments
4 months ago
JimmyRacheta
2 points
116.
▲
Show HN: EdgeAI-OS – Air-gapped Linux distro where AI is a system primitive
2 comments
4 months ago
neuralweaves
2 points
117.
▲
Show HN: Veritas OS – Local OS for LLM Governance
github.com/veritasfuji-japan
2 comments
7 months ago
VERITAS_OS_JP
2 points
118.
▲
Show HN: Cordon – Security gateway for MCP tool calls with HITL approvals
github.com/marras0914
1 comment
2 months ago
babas03
2 points
119.
▲
We scanned 73 open-source MCP servers. Here's what source code analysis found
1 comment
3 months ago
sigildev
2 points
120.
▲
Show HN: SafeAgent – exactly-once execution guard for AI agents
1 comment
4 months ago
Lions2026
2 points
More