HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
481.
▲
Peaky Peek – Local-first debugger for AI agents
github.com/acailic
discuss
3 months ago
ilkehimself
1 points
482.
▲
Show HN: 96.2% on LongMemEval – world record, built solo in 16 days for $1k
github.com/JordanMcCann
discuss
3 months ago
JordanMcCann
1 points
483.
▲
ToolTrust Scanner – detect backdoored MCP packages (litellm 1.82.8)
github.com/AgentSafe-AI
discuss
3 months ago
brian93512
1 points
484.
▲
Agentfab – A stateful, distributed multi-agent framework
github.com/RazvanMaftei9
discuss
3 months ago
razvan_maftei
1 points
485.
▲
Show HN: Agent-IM – IM, but for Agents
github.com/LinklyAI
discuss
3 months ago
blueeon
1 points
486.
▲
Agent Control – agentic runtime guardrails
github.com/agentcontrol
discuss
3 months ago
samgdf2
1 points
487.
▲
Show HN: Agentic Algorithm Engineering
github.com/CHSZLab
discuss
3 months ago
0x23
1 points
488.
▲
Show HN: AgentClick – Human-in-the-loop review UI for AI coding agents
github.com/agentlayer-io
discuss
3 months ago
harvenstar
1 points
489.
▲
Multi-agent fleet management for coding agents
github.com/supaku
discuss
3 months ago
mooreds
1 points
490.
▲
Agent-sync – sync between Claude Code and Codex configs
github.com/matanabudy
discuss
3 months ago
matanabudy
1 points
491.
▲
Show HN: AgentUQ, a token-logprob runtime gate for LLM agents
github.com/antoinenguyen27
discuss
3 months ago
AntoineN2
1 points
492.
▲
Agentic Harness Bootstrap
github.com/synthnoosh
discuss
4 months ago
synthnoosh
1 points
493.
▲
Agentcontainer: A standard way to declare agent containers for your projects
github.com/jpmelos
discuss
4 months ago
jpmelos
1 points
494.
▲
Show HN: I built AgentSafety, an open benchmark for coding-agent safety
github.com/serkanaltuntas
discuss
4 months ago
serkanaltuntas
1 points
495.
▲
Show HN: I open-sourced the AI agents I use to run 35 marketing clients solo
github.com/TheCMOAI
discuss
4 months ago
nsyno
1 points
496.
▲
Evalien – Node.js event loop agent harness
github.com/agentbellnorm
discuss
4 months ago
agentbellnorm
1 points
497.
▲
Show HN: An API that AI agents can discover, register, and pay for themselves
github.com/techromp
discuss
4 months ago
techromp
1 points
498.
▲
AAP: A portable, composable spec for AI agents taking action in the world
github.com/agentactionprotocol
discuss
4 months ago
mooreds
1 points
499.
▲
Aegis - A safe, auditable, replayable agentic guardrails framework
github.com/agentlifylabs
discuss
4 months ago
aposded
1 points
500.
▲
Show HN: Agent-Audit – Lint and cost-estimate your AI agent
github.com/AreteDriver
discuss
4 months ago
aretedriver
1 points
501.
▲
Show HN: Agentic Power of Attorney (APOA) – An open standard for AI agent auth
github.com/agenticpoa
discuss
4 months ago
juanfiguera
1 points
502.
▲
Show HN: A Claude Code hook that sends you to bed
github.com/ElleNajt
discuss
4 months ago
ellenajt
1 points
503.
▲
Show HN: Local knowledge vault plugin for Claude Code
github.com/aneequrrehman
discuss
4 months ago
aneequrrehman
1 points
504.
▲
Show HN: TuFT – Open-source multi-tenant, Tinker-compatible fine-tuning platform
github.com/agentscope-ai
discuss
4 months ago
ekzhu
1 points
505.
▲
Show HN: AgentDX – Open-source linter and LLM benchmark for MCP servers
github.com/agentdx
discuss
4 months ago
yamarldfst
1 points
506.
▲
Show HN: AgentPump – AI agents launch tokens on Solana (Android)
github.com/agentpump
discuss
4 months ago
AgentPump
1 points
507.
▲
Show HN: Agent Audit Kit v0.1 – deterministic replay + stress for LLM agents
github.com/helpfuldolphin
discuss
4 months ago
helpfuldolphin
1 points
508.
▲
Show HN: Agent Breadcrumbs – Unified Work Log Across Claude, Codex, OpenClaw
github.com/ejcho623
discuss
4 months ago
ejcho623
1 points
509.
▲
Show HN: AgentKV – SQLite for AI agent memory (MMAP vector+graph DB)
github.com/DarkMatterCompiler
discuss
4 months ago
shiwang_khera
1 points
510.
▲
AgentProbe – adversarial security testing for AI agents (134 attack patterns)
github.com/alexmelges
discuss
4 months ago
alexmelges
1 points
More