Search: github.com/Mokens | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

Show HN: Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill

github.com/LegalRabbit-AI

5 days ago

5 points

62.

Petals runs Llama 2 (70B) from Colab at 5 tokens/sec

github.com/bigscience-workshop

3 years ago

5 points

63.

Ask HN: How do you give AI agents real codebase context without burning tokens?

4 months ago

5 points

64.

Use BERT to get sentence and tokens embedding in an easier way

github.com/imgarylai

7 years ago

5 points

65.

ANP – A binary protocol for AI agent-to-agent price negotiation (no LLM tokens)

github.com/victornominista

2 months ago

5 points

66.

Anonymous Authentication: Creating access tokens for guest accounts

github.com/zitadel

4 months ago

5 points

67.

How to calculate alignment between BERT and spaCy tokens effectively and robust

gist.github.com

6 years ago

5 points

68.

Fable 5 burns tokens fast. I found an cost tracker for it

github.com/tigerless-labs

10 days ago

4 points

69.

Tool to reduce AI tokens and generate more detailed and accurate PRDs

github.com/Corbell-AI

3 months ago

4 points

70.

Compress tool outputs, logs, files, RAG chunks before LLM for 60-95% less tokens

github.com/chopratejas

3 days ago

4 points

71.

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

github.com/deepfence

a month ago

4 points

72.

Agent Braille – 8-bit state encoding for LLM agents, ~92% fewer tokens than JSON

github.com/Tetrahedroned

a month ago

4 points

73.

Ane: CLI editor that uses LSPs to let agents explore/edit code with fewer tokens

github.com/prettysmartdev

a month ago

4 points

74.

A Compression Tool for LLM Reads. Est. 60-95% Fewer Tokens

github.com/chopratejas

a month ago

4 points

75.

JWT Studio – Your local tokens, organized

github.com/MiguelRipoll23

4 months ago

4 points

76.

Show HN: A Zero-Copy 1.58-bit LLM Engine hitting 117 Tokens/s on single CPU core

github.com/r3-engine

5 months ago

4 points

77.

SSH – Spoofing FIDO2 Tokens Presentation

github.com/ssh-mitm

5 years ago

4 points

78.

Show HN: Standalone (i.e. no-server) test and reference code for FIDO U2F tokens

github.com/rongarret

10 years ago

4 points

79.

IETF spec to allow bypass challenge pages via signed tokens that gives anonymity

github.com/cloudflare

10 years ago

4 points

80.

Protocol for bypassing challenge pages using RSA blind signed tokens

github.com/cloudflare

10 years ago

4 points

81.

Show HN: Zonformat– 35–60% fewer LLM tokens using zero-overhead notation

6 months ago

3 points

82.

Show HN: Handoff – preserve coding context when agents run out of tokens

github.com/TStansel

a month ago

3 points

83.

Claude Code alternative: same output quality, 10x less input tokens used

github.com/Simon-Free

2 months ago

3 points

84.

Show HN: Syntax Highlighter for VSCode – Tree-Sitter and Semantic Tokens

github.com/EvgeniyPeshkov

6 years ago

3 points

85.

Getting the right answer the first time, is how you save time and tokens

github.com/joreag

2 months ago

3 points

86.

Add 500M tokens of context space to any LLM with <300ms latency

3 months ago

3 points

87.

Show HN: Spend weekend Claude tokens making your code bulletproof with Lean

github.com/savarin

3 months ago

3 points

88.

Tell HN: Adding congestion control and retry tokens to a reliable UDP transport

3 days ago

3 points

89.

Token-saviour – routing skill for AI agent tool selection (~70% fewer tokens)

github.com/vagkaratzas

7 days ago

3 points

90.

Local firewall for AI Agents that cuts tokens usage and cost by 40–70%

github.com/ashp15205

11 days ago

3 points