Search: github.com/cos | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

571.

Runcap, I built a local cost cap for coding agents (github.com/kirder24-code)

1 point

2 days ago

572.

Claude Code cost observability to prevent tokenmaxxing (github.com/delta-hq)

1 point

24 days ago

573.

Show HN: Ungate – use Claude and GPT subscriptions in Cursor without API costs (github.com/orchidfiles)

1 point

24 days ago

574.

LLM-test-kit – Test consistency, latency, cost and behavior of LLM apps (github.com/muskanjoshi01)

1 point

a month ago

575.

Sqz: Compress LLM context to save tokens and reduce costs (github.com/ojuschugh1)

1 point

a month ago

576.

I reversed Opus 4.7 costs (github.com/LucasDuys)

1 point

2 months ago

577.

Save 50–60% on token costs with OpenClaw and Tamp (github.com/sliday)

1 point

2 months ago

578.

Show HN: AI Cost Firewall – OpenAI-compatible gateway with semantic caching (github.com/vcal-project)

1 point

2 months ago

579.

Burn0 – Track every API cost in your Node.js app with one import (github.com/burn0-dev)

1 point

2 months ago

580.

Free open source AI cost tracker – pip install tokenbudget (github.com/AIMasterLabs)

1 point

3 months ago

581.

Show HN: Metrx – auto optimize AI agents for ROI and rvenue, not just cost (github.com/metrxbots)

1 point

3 months ago

582.

Warp-types: GPU shuffle UB becomes a compile error (Rust, Lean proof, zero cost) (github.com/modelmiser)

1 point

3 months ago

583.

Verified orchestration and cost tracking for Copilot CLI (github.com/moonrunnerkc)

1 point

3 months ago

584.

Aitracker – Track Claude, Codex, Gemini usage and costs from your terminal (github.com/j0nl1)

1 point

3 months ago

585.

Show HN: NadirClaw, LLM router that cuts costs by routing prompts right (github.com/doramirdor)

1 point

4 months ago

586.

Show HN: CleanCloud – 20 rules to find what's costing you money in AWS and Azure

1 point

4 months ago

587.

Show HN: Codesession-CLI – Teach your AI agent to track its own token costs

1 point

4 months ago

588.

Show HN: Headroom – Reversible context compression for LLMs(~60% cost reduction) (github.com/chopratejas)

1 point

5 months ago

589.

Most LLM cost isn't compute – it's identity drift (110-cycle GPT-4o benchmark) (github.com/sigmastratum)

1 point

6 months ago

590.

Open-source Live2D avatar pipeline – 80-95% cost reduction using Gemini (gist.github.com)

1 point

7 months ago

591.

N8n community node – cascadeflow, Reduce AI costs 30-65% with model cascading (github.com/lemony-ai)

1 point

7 months ago

592.

Show HN: Autocache – Cut Claude API costs 90% (for n8n, Flowise, etc.) (github.com/montevive)

1 point

8 months ago

593.

MinionS Protocol – Cost-Efficient Local-Remote LLM Collaboration (github.com/docker)

1 point

9 months ago

594.

AIClient-2-API, a Practical Solution to Reduce LLM Usage Costs (github.com/justlovemaki)

1 point

10 months ago

595.

Cognify: Automated Quality+Cost Optimization for GenAI Workflow (github.com/GenseeAI)

1 point

2 years ago

596.

StarryDex – A Pokédex application for the COSMIC desktop written in Rust (github.com/mariinkys)

1 point

2 years ago

597.

Benchcfe – Cost for Efficiency Benchmark Tool (github.com/alfonsodg)

1 point

3 years ago

598.

Use LLM (ChatGPT) to analyze optimize your cloud costs (github.com/web3tej)

1 point

3 years ago

599.

Show HN: Atorable-React – Faster PageSpeed, Less Load, Lower Costs (github.com/Atorable)

1 point

4 years ago

600.

Ask HN: Low-Cost Lane-Level Positioning Using Optimized Time Series GNSS & IMU (github.com/MapIV)

1 point

5 years ago