Search: github.com/LMMS | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

571.

Show HN: Chatroom app to interact with multiple LLMs in real-time (github.com/russellballestrini)

3 points

3 years ago

572.

Show HN: DistiLlama Summarize Web Pages with Local LLMs (github.com/shreyaskarnik)

3 points

3 years ago

573.

Open Sourcing Remembrall: A Long-Term Memory Proxy for LLMs (github.com/reductoai)

3 points

raunakchowdhuri

3 years ago

574.

Show HN: Simple HTTP API for LLMs (github.com/cmitsakis)

3 points

3 years ago

575.

Our latest project: fact-checking for LLMs (github.com/kortex-labs)

3 points

3 years ago

576.

Salience: Automatic text highlights with LLMs and TextRank (github.com/mattneary)

3 points

3 years ago

577.

Easy to use Python library for retrieval in LLMs apps (github.com/gigagiova)

3 points

3 years ago

578.

A 400-hour forensic audit of LLMs using multi-model context saturation (github.com/alanscalone)

3 points

13 days ago

579.

Patchwork: AST-Native Editing for LLMs (github.com/ThatXliner)

3 points

a month ago

580.

Everything Vault – a local-first Markdown knowledge system for LLMs (github.com/AntlerForge)

3 points

a month ago

581.

A representation model as a workaround for catastrophic forgetting in LLMs (gist.github.com)

3 points

a month ago

582.

Show HN: I built a search engine for llms.txt sites (statespace.com)

3 points

a month ago

583.

1-week open source challenge using resilient LLMs (github.com/gitcommitshow)

3 points

2 months ago

584.

Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs

3 points

2 months ago

585.

AET: A transpiler that compresses code for LLMs (saves 30-55% tokens) (github.com/liminnnng-art)

3 points

2 months ago

586.

Airupt – open-source red-teaming for LLMs (79 attack vectors) (github.com/airupt)

3 points

2 months ago

587.

The Open Source AI Engineering Platform for Agents, LLMs and Models (github.com/mlflow)

3 points

2 months ago

588.

MoralStack: A deliberative policy layer for LLMs (github.com/fdidonato)

3 points

2 months ago

589.

Show HN: FC-Eval – CLI to Benchmark Local or Cloud LLMs on Function Calling (github.com/gauravvij)

3 points

3 months ago

590.

A structural epistemic limit in LLMs: 8–15% unverifiable claims across domains (github.com/elly99-AI)

3 points

3 months ago

591.

Show HN: Godshell – Talking in Natural Language to Your Kernel via eBPF and LLMs (github.com/raulgooo)

3 points

3 months ago

592.

Show HN: Let LLMs anonymously report tool quality back to MCP servers (github.com/modelcontextprotocol)

3 points

3 months ago

593.

LeBron James Is President – Exploiting LLMs via "Alignment" Context Injection (github.com/skavanagh)

3 points

3 months ago

594.

Show HN: oMLX – coding agents on local LLMs without the painful reprefill (github.com/jundot)

3 points

3 months ago

595.

Show HN: Cobalt – Unit tests for AI agents, like Jest but for LLMs (github.com/basalt-ai)

3 points

4 months ago

596.

Show HN: Prompts are coupled to LLMs and nobody builds tooling for it (github.com/shakecodeslikecray)

3 points

4 months ago

597.

Show HN: Lineark – Linear CLI and Rust SDK for Humans and LLMs (github.com/flipbit03)

3 points

4 months ago

598.

Show HN: Google Search MCP for local LLMs – 14 tools, no API key (github.com/VincentKaufmann)

3 points

4 months ago

599.

Show HN: Stigmergy pattern for multi-agent LLMs (80% fewer API calls) (github.com/KeepALifeUS)

3 points

4 months ago

600.

Show HN: Interactive Terminal for AI – Let LLMs Drive TTYs (github.com/mstsirkin)

3 points

5 months ago