HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
61.
▲
I built an open-weights memory system that reaches 80.1% on the LoCoMo benchmark
2 comments
7 months ago
ViktorKuz
2 points
62.
▲
Show HN: Middleware for translating between AI agent protocols
github.com/kwstx
1 comment
3 months ago
kwstx
2 points
63.
▲
Show HN: CtxVault – agent memory isolation enforced outside app code
1 comment
4 months ago
FiloVenturini
2 points
64.
▲
Show HN: Lilith-zero update: fast Rust security for agents
github.com/BadC-mpany
discuss
2 months ago
gregojaca
2 points
65.
▲
Show HN: A2A Utils – a comprehensive set of utility functions for A2A servers
github.com/a2aproject
discuss
2 months ago
benclarkeio
2 points
66.
▲
Show HN: A test harness that blocks unsafe AI actions before execution
discuss
3 months ago
celestinestudio
2 points
67.
▲
Show HN: Mapping 10 years of world model research (489 papers, 2012–2026)
github.com/Bowen12137
discuss
4 months ago
Arthur12137
2 points
68.
▲
Show HN: AFS – filesystem-native memory layer for AI agents
discuss
4 months ago
thompson0012
2 points
69.
▲
Show HN: PolyMCP – MCP Tools, Autonomous Agents, and Orchestration
discuss
4 months ago
justvugg
2 points
70.
▲
Show HN: AI Agent Architecture Patterns for Production Systems
github.com/devwithmohit
discuss
5 months ago
mohitdevops
2 points
71.
▲
Show HN: Memory System Hitting 80.1% Accuracy on LoCoMo (Built in 4.5 Months)
github.com/vac-architector
discuss
7 months ago
ViktorKuz
2 points
72.
▲
Show HN: Open-Source] Deep Research Assistant Built Solely for Gemini API
github.com/zyakita
discuss
10 months ago
zyakita
2 points
73.
▲
Show HN: Maia – Open-source framework for testing AI systems before deployment
maiaframework.com
discuss
10 months ago
radoslaw-sz
2 points
74.
▲
Show HN: Runtime – skills-based browser automation that uses fewer tokens
github.com/runtime-org
discuss
10 months ago
tito777
2 points
75.
▲
Show HN: An open-source AI Quant Agent trading live with my own $1000
github.com/chenjy16
2 comments
3 months ago
chenjy16
1 points
76.
▲
Show HN: PolyMCP – open-source toolkit to expose MCP tools and run agents
2 comments
5 months ago
justvugg
1 points
77.
▲
Show HN: QonQrete – Local-first multi-agent system for sandboxed code generation
github.com/illdynamics
2 comments
6 months ago
illdynamics
1 points
78.
▲
Show HN: MPLP – Why Prompt Engineering Is over (Protocol Engineering Begins)
github.com/Coregentis
2 comments
7 months ago
CoregentisAI
1 points
79.
▲
Show HN: MirrorNeuron – an open-source runtime for reliable on-device AI agents
mirrorneuron.io
1 comment
2 months ago
homerquan
1 points
80.
▲
Show HN: Why LLM Personas Collapse and How Structural Identity Fixes It
1 comment
4 months ago
WujieGuGavin
1 points
81.
▲
Show HN: CtxVault – Local memory control layer for multi-agent AI systems
1 comment
4 months ago
FiloVenturini
1 points
82.
▲
Show HN: Pairl – Protocol for Agent Communication with Budget Tracking
github.com/dwehrmann
1 comment
5 months ago
dwehrmann
1 points
83.
▲
Show HN: Hyperterse – a super fast runtime to connect your data to your agents
github.com/hyperterse
1 comment
5 months ago
samrith
1 points
84.
▲
Show HN: MeshCore – Why do I have to build every agent from scratch?
meshcore.ai
1 comment
8 months ago
antenehmtk
1 points
85.
▲
Show HN: strangeClaw – a self-hosted agent running inside a Firecracker microVM
github.com/itsthestranger
discuss
12 days ago
pstrange
1 points
86.
▲
Show HN: AI agents who prevent context drift through gossip
wuphf.team
discuss
a month ago
najmuzzaman
1 points
87.
▲
Show HN: OneManCompany The first AI company with real corporate org structure
one-man-company.com
discuss
2 months ago
yuzhengxu
1 points
88.
▲
Show HN: SafeAgent – exactly-once execution guard for AI agent side effects
discuss
3 months ago
Lions2026
1 points
89.
▲
Show HN: AgentUQ, a token-logprob runtime gate for LLM agents
github.com/antoinenguyen27
discuss
3 months ago
AntoineN2
1 points
90.
▲
Show HN: A step debugger for AI agents
github.com/SEsquieu
discuss
3 months ago
sesquieu
1 points
More