Search: github.com/memo | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

271.

Show HN: MemoLock – Distributed Caching with Promises

github.com/kristoff-it

7 years ago

4 points

272.

Show HN: VSCode Working Memory – Capture everything in a single text file

github.com/atomashevic

4 years ago

3 points

273.

Show HN: Memory for LLM apps that cuts input tokens up to 80% (avg 68%)

github.com/Tem-Degu

a month ago

3 points

274.

Show HN: I built an agent memory system for myself and got 90.8% on LongMemEval

github.com/shane-farkas

2 months ago

3 points

275.

Linting for Your Docs

github.com/a24z-ai

9 months ago

fernandoramlugo

3 points

276.

You're doing context engineering wrong

github.com/a24z-ai

10 months ago

3 points

277.

Made a Simple Memory Indicator for macOS Status Bar. Made Me Happy

github.com/gs-asrivastav

7 years ago

3 points

278.

They Say AI Will Replace Programmers. I Think AI Will Mass-Produce Them Instead

github.com/vac-architector

7 months ago

2 points

279.

Show HN: Go Implementation of Redis MemoLock – Distributed Caching with Promises

github.com/kristoff-it

7 years ago

2 points

280.

Elo Memory – Bio-inspired episodic memory for AI agents (free, open source)

github.com/server-elo

3 months ago

2 points

281.

Show HN: VAC Memory – 80.1% LoCoMo accuracy vs. Mem0's 68%

github.com/vac-architector

7 months ago

2 points

282.

Show HN: I built an LLM that never forgets – persistent user memory with RAG

github.com/skorotkiewicz

8 months ago

2 points

283.

Show HN: Squash – your browsing history as context for ChatGPT

github.com/kstonekuan

a year ago

2 points

284.

Lamini Memory Tuning: near-perfect fact recall via 1M-way MoE [pdf]

github.com/lamini-ai

2 years ago

2 points

285.

Two orders of magnitude faster Persistent AI memory via a binary lattice

github.com/RYJOX-Technologies

4 months ago

1 points

286.

VAC Memory System – SOTA RAG (80.1% LoCoMo) Built by a Handymen Using Claude CLI

github.com/vac-architector

7 months ago

1 points

287.

CUDA Unified Memory Analyzer – measure what your GPU is doing with memory

github.com/parallelArchitect

4 months ago

1 points

288.

Most LLM conversations are noise: a cheap way to decide what to remember

github.com/zachseven

6 months ago

1 points

289.

Show HN: MCA-Entity Coverage as a Memory Retrieval Gate

github.com/vac-architector

7 months ago

1 points

290.

Long-term memory (LTM) extension for oobabooga's Text Generation Web UI

github.com/wawawario2

3 years ago

1 points

291.

Show HN: Google ADK and Vertex AI Memory Bank for Persistent Conversational AI

github.com/serkanh

a year ago

1 points

292.

Banishing LLM hallucinations requires rethinking generalization [pdf]

github.com/lamini-ai

2 years ago

itunpredictable

1 points

293.

A default Rails install takes up to 40M

github.com/penso

11 years ago

1 points

294.

Show HN: Zep – Long-Term Memory Store for LLM Apps

3 years ago

7 points

295.

Some ios kernel analysis tool write by C

9 years ago

6 points

296.

Show HN: Bossa – Persistent filesystem memory for AI agents via MCP or CLI

3 months ago

2 points

297.

Show HN: DiffMem in production, Git-based AI memory

4 months ago

2 points

298.

Show HN: PgQueuer – A PostgreSQL job queue that works without PostgreSQL

github.com/janbjorge

4 months ago

2 points

299.

Ask HN: How do you keep AI assistants consistent with your personal preferences?

9 months ago

1 points

300.

Modern 8bit Computer as an Art

github.com/dmytrostriletskyi

5 years ago

87 points