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