HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
61.
▲
Kimi K2.5 is confident that it is Claude
gist.github.com
discuss
4 months ago
Aarvay
1 points
62.
▲
Kimrio357 Gmail.com
github.com/kamranahmedse
discuss
6 months ago
kimrio
1 points
63.
▲
Kosong: Kimi AI's Agent SDK
github.com/MoonshotAI
discuss
7 months ago
diptanu
1 points
64.
▲
Launch HN: Cactus (YC S25) – AI inference on smartphones
github.com/cactus-compute
63 comments
9 months ago
HenryNdubuaku
123 points
65.
▲
Show HN: Fine-tuned Llama 3.2 3B to match 70B models for local transcripts
bilawal.net
8 comments
10 months ago
phantompeace
31 points
66.
▲
Ask HN: What might be the future of open-source offline-first email apps?
18 comments
9 years ago
mwcampbell
27 points
67.
▲
Show HN: I built a database for AI agents
github.com/DinobaseHQ
10 comments
2 months ago
Kappa90
12 points
68.
▲
Show HN: Fabro – open-source dark software factory
github.com/fabro-sh
discuss
3 months ago
brynary
7 points
69.
▲
Show HN: Achieves Perfect 100 Score Across 6 Leading AI Model Evaluations
github.com/onestardao
8 comments
a year ago
TXTOS
6 points
70.
▲
Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090
github.com/Luce-Org
1 comment
2 months ago
GreenGames
6 points
71.
▲
Show HN: Eliezer – Tiny (~7K LOC) Self-Hosted AI Agent (PWA, Self-Editing)
eliezer.app
1 comment
4 months ago
dvictor
6 points
72.
▲
Show HN: AI Paul Graham
paulgraham-nia.com
5 comments
7 months ago
arlanrakh
4 points
73.
▲
Show HN: Agent Runner – open-source agent harness to benchmark real coding
designarena.ai
discuss
7 months ago
grace77
4 points
74.
▲
Show HN: I blind-tested 14 LLMs on a WP plugin task. Surprising Findings
github.com/guilamu
2 comments
2 months ago
guilamu
3 points
75.
▲
Show HN: HashMeterAi – Private AI Token Real Usage Meter for All Models
github.com/Hash-7777
1 comment
7 days ago
Hash7777
3 points
76.
▲
SIP Client for WEBRTC
github.com/Quobis
discuss
13 years ago
eloycoto
3 points
77.
▲
Show HN: Free Unlimited Claude Code Usage with Nvidia Nim Models
github.com/Alishahryar1
discuss
5 months ago
AliShahryar
3 points
78.
▲
Show HN: RightSize CLI, Find the cheapest LLM that works for your prompt
github.com/NehmeAILabs
discuss
5 months ago
44za12
3 points
79.
▲
Show HN: OpenClaw remembers for OpenClaw. Sekha remembers for your full workflow
sekha.dev
1 comment
4 months ago
sekha-ai
2 points
80.
▲
Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir
github.com/caudena
discuss
4 days ago
caudena
2 points
81.
▲
Show HN: Perstack – Containerized harness, 5 tests with full logs and API cost
github.com/perstack-ai
discuss
3 months ago
FL4TLiN3
2 points
82.
▲
Show HN: Polymcp Implements Ollama for Local and Cloud Model Execution
discuss
5 months ago
justvugg
2 points
83.
▲
Show HN: Framework to structure LLM dev workflows with Markdown-based protocol
github.com/Fr-e-d
discuss
a year ago
Fr-e-d
2 points
84.
▲
Show HN: Vilberta: speech to speech/text chatbot
github.com/charstorm
2 comments
5 months ago
graphitout
1 points
85.
▲
Show HN: InkSight – An open-source, LLM-powered e-ink display for "slow info"
github.com/datascale-ai
1 comment
4 months ago
xx123122
1 points
86.
▲
Show HN: RepoGauge – save token costs and compare agents on your own repos
repogauge.org
discuss
2 months ago
siliconc0w
1 points
87.
▲
Show HN: Claude-consensus – Multi-model code review plugin for Claude Code
github.com/AltimateAI
discuss
4 months ago
k_git
1 points
88.
▲
Show HN: InkSight – An open-source, LLM-powered e-ink display for "slow info"
github.com/datascale-ai
discuss
4 months ago
xx123122
1 points
89.
▲
Show HN: Preference-aware routing for OpenClaw via Plano
github.com/katanemo
discuss
4 months ago
sparacha
1 points
90.
▲
Show HN: Roe.md generate your own OpenClaw-like bot from a single Markdown file
github.com/guld
discuss
4 months ago
guld
1 points
More