Search: github.com/mudge | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

211.

macOS Desktop app v0.0.1 Preview Release "bot with a budget" idea

github.com/DialtoneApp

2 months ago

1 points

212.

ReceiptBot – Stop Node.js AI agents from reading .env and burning your budget

github.com/redshadow912

2 months ago

LocalhostLegend

1 points

213.

Show HN: Run untrusted WASM plugins with CPU/mem/network/file budgets

github.com/akgitrepos

4 months ago

1 points

214.

Show HN: Satgate-proxy – Hard budget caps for MCP tool calls (zero deps, npx)

github.com/SatGate-io

4 months ago

1 points

215.

Show HN: Pairl – Protocol for Agent Communication with Budget Tracking

github.com/dwehrmann

5 months ago

1 points

216.

Should I turn my open-source project into a product with a $5k budget?

github.com/Luthiraa

5 months ago

luthiraabeykoon

1 points

217.

Show HN: EvalView pytest style tests for AI agents (budgets, hallucinations)

github.com/hidai25

6 months ago

1 points

218.

Show HN: USure – Nudge to reduce browsing

12 years ago

1 points

219.

Show HN: Fiscal – An Agent Friendly CLI for Actual Budget

4 months ago

1 points

220.

Show HN: Claude-relais – A plan/build/judge loop mixing Claude with Cursor

github.com/clementrog

4 months ago

1 points

221.

Show HN: SatGate – Budget enforcement proxy for MCP tool calls (L402/macaroons)

4 months ago

1 points

222.

Show HN: SVGV – A Real-Time Vector Video Format for Budget Hardware

github.com/thealidev

5 months ago

1 points

223.

Show HN: SLOK – A Kubernetes operator for declarative SLOs and error budgets

github.com/federicolepera

5 months ago

1 points

224.

Show HN: TensorWall – Open-source LLM gateway with budget controls and security

github.com/datallmhub

6 months ago

1 points

225.

Precision-Based Sampling of LLM Judges

a year ago

1 points

226.

Private LLM on a Budget: Deploy on Paperspace with Terraform and Ansible

github.com/jevy

2 years ago

1 points

227.

Show HN: Lone Arena – Self-hosted LLM human evaluation, you be the judge

github.com/Contextualist

2 years ago

1 points

228.

Collection of TypeScript type challenges with online judge

github.com/type-challenges

2 years ago

1 points

229.

Gimbal helps maintain web performance budgeting in CLI and CI

github.com/ModusCreateOrg

7 years ago

1 points

230.

U.S. Federal Budget Flirts with Surplus Using Special Items

github.com/axibase

8 years ago

1 points

231.

Show HN: A self hosted online judge for meetups and workshops, written in Go

github.com/MohamedBassem

9 years ago

1 points

232.

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

github.com/cactus-compute

a month ago

776 points

233.

Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks

github.com/antoinezambelli

a month ago

687 points

234.

Launch HN: Lago (YC S21) – Open-source usage-based billing

3 years ago

442 points

235.

Show HN: Lathe – Use LLMs to learn a new domain, not skip past it

github.com/devenjarvis

16 days ago

402 points

236.

Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

github.com/moonshine-ai

4 months ago

316 points

237.

Show HN: Bagels – TUI expense tracker

github.com/EnhancedJax

a year ago

283 points

238.

Launch HN: Stack Auth (YC S24) – An Open-Source Auth0/Clerk Alternative

github.com/stack-auth

2 years ago

280 points

239.

Show HN: Plandex v2 – open source AI coding agent for large projects and tasks

github.com/plandex-ai

a year ago

257 points

240.

Show HN: Openpanel – An open-source alternative to Mixpanel

github.com/Openpanel-dev

2 years ago

244 points