Search: github.com/tockins | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

WebSocket+Huffman vs. SSE+JSON for streaming LLM tokens

github.com/vidur2

4 months ago

1 points

152.

Show HN: Arc – A language that uses 27-63% fewer tokens than JavaScript

github.com/kai-builds-ai

4 months ago

1 points

153.

Show HN: PageMap – MCP server that compresses web pages from 100K to 2-5K tokens

github.com/Retio-ai

4 months ago

1 points

154.

Constant 14ms attention: 512→524K tokens (24.5x faster than FlashAttention)

github.com/RegularJoe-CEO

5 months ago

1 points

155.

We added TOON compression to our LLM gateway – compress prompts, saves tokens

github.com/toon-format

5 months ago

1 points

156.

Show HN: HoneypotScan – Detect crypto scam tokens

github.com/Teycir

5 months ago

1 points

157.

Show HN: gpt-cache – A OSS proxy cache to save on GPT tokens and response times

github.com/jwtly10

2 years ago

1 points

158.

Kubernetes API smuggles its authorization tokens via fake WebSocket protocols

github.com/whatwg

3 years ago

1 points

159.

SecretScanner is an open-source tool for discovering passwords, API, tokens

github.com/deepfence

a month ago

1 points

160.

Find where your AI coding tokens went: local TUI for Codex/Claude logs

github.com/peterxcli

a month ago

1 points

161.

Token Dashboard – local desktop app to see where your Claude Code tokens go

github.com/Arylmera

a month ago

1 points

162.

Ask HN: At ~165k tokens, does Opus 4.6 1M outperform Opus 4.6 200k?

2 months ago

1 points

163.

Show HN: MESI cache coherence for multi-agent LLM context sync – 95% less tokens

github.com/hipvlady

2 months ago

1 points

164.

Show HN: Rocky-Project Hail Mary agent skill that cut output tokens ~47%

github.com/hpbyte

2 months ago

1 points

165.

I built a local dashboard to inspect Claude Code sessions, tokens, and costs

github.com/Arindam200

3 months ago

1 points

166.

Log Reducer – Cut 50-90% of tokens when your AI debugs logs (MCP tool and CLI)

github.com/launch-it-labs

3 months ago

1 points

167.

Show HN: Nostr DM bot – control OpenCode/Cursor via DMs, pay with cashu tokens

github.com/dhalsim

4 months ago

1 points

168.

Show HN: TableCraft – Stop burning AI tokens on table boilerplate

github.com/jacksonkasi1

4 months ago

1 points

169.

Show HN: AgentPump – AI agents launch tokens on Solana (Android)

github.com/agentpump

4 months ago

1 points

170.

Use your leftover CC/Codex tokens overnight for maintenance PRs

github.com/marcus

4 months ago

1 points

171.

Prepaid Lightning tokens as API keys for AI agents

4 months ago

1 points

172.

Show HN: O(1) memory attention – 512K tokens in 3.85 GB (eval binary)

github.com/RegularJoe-CEO

5 months ago

1 points

173.

Show HN: Proxy MCP server that lazy loads tools to save tokens

github.com/mquan

5 months ago

1 points

174.

Show HN: Slim – 50% fewer tokens than JSON for LLM applications

github.com/matteuccimarco

5 months ago

1 points

175.

Qsp: A simple S-Expression parser for Rust TokenStreams

github.com/KnorrFG

6 months ago

1 points

176.

Full v0 by Vercel System Prompt (10K+ tokens)

github.com/x1xhlol

7 months ago

1 points

177.

Show HN: TokenX – Track LLM API cost, latency and tokens with one decorator

github.com/dvlshah

a year ago

1 points

178.

Show HN: OpenAI API Token Tracker – Stop Overpaying for Tokens

github.com/limonene213u

a year ago

1 points

179.

Longest Chinese Tokens in Gpt4o

gist.github.com

2 years ago

1 points

180.

Show HN: gpt-cache – A OSS proxy cache to save on GPT tokens and response times

github.com/jwtly10

2 years ago

1 points