Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
631.
▲
Graft – semantic memory for AI agents, without the LLM
(github.com/AEndrix03)
4 points
AEndrix03
a month ago
discuss
632.
▲
Show HN: Local-first long-term memory engine for AI agents·MCP/CLI· 100% local
(github.com/misaelzapata)
4 points
misaelzapata
a month ago
discuss
633.
▲
Ctx – Persistent Memory for Claude Code, Cursor, and AI Coding Tools
(github.com/ActiveMemory)
4 points
parlakisik
a month ago
discuss
634.
▲
Show HN: Graph-based memory for local LLMs with multi-hop not just vector search
(github.com/Lumen-Labs)
4 points
Chrisszz
a month ago
discuss
635.
▲
Mnemo – a local-first notepad that acts as memory for AI agents
(github.com/fwgadmin)
4 points
mhome9
2 months ago
discuss
636.
▲
Show HN: Self-improving agent memory system, 92% R 5 LongMemEval, PostgreSQL
(github.com/salishforge)
4 points
artificium
2 months ago
discuss
637.
▲
C++ standard libray with automated memory management
(github.com/pg83)
4 points
pshirshov
2 months ago
discuss
638.
▲
Zprof – a comptime-configurable and minimal memory profiler for Zig allocators
(github.com/ANDRVV)
4 points
andrvv
2 months ago
discuss
639.
▲
Smalloc: A simple memory allocator
(github.com/zooko)
4 points
todsacerdoti
5 months ago
discuss
640.
▲
Hyperion – Bypass the OS: cooperative fibers and signal-driven memory management
(github.com/farukalpay)
4 points
rescueteam
5 months ago
discuss
641.
▲
PowerMem – Persistent memory layer for AI agents
(github.com/oceanbase)
4 points
jinqueeny
5 months ago
discuss
642.
▲
Show HN: Agent Skill turns existing filesystem into Claude's memory
(github.com/backnotprop)
4 points
ramoz
6 months ago
discuss
643.
▲
MemMachine, an open-source memory layer for advanced AI agents
(github.com/MemMachine)
4 points
jinqueeny
7 months ago
discuss
644.
▲
MindShard: A Self-Hosted Semantic Memory Layer for Your Browsing
(github.com/izeigerman)
4 points
s0ck_r4w
7 months ago
discuss
645.
▲
Show HN: Core – open-source memory graph for AI agents (88.24% SOTA on LoCoMo)
(blog.heysol.ai)
4 points
Manik_agg
9 months ago
discuss
646.
▲
Show HN: I love ChatGPT Memory, so I built one
(github.com/memodb-io)
4 points
gusye
10 months ago
discuss
647.
▲
Totally Safe: Memory Vulnerabilities in Safe Rust
(github.com/viktorlott)
4 points
ubj
10 months ago
discuss
648.
▲
Memory-wise & fast trie for Python (may use 50x-100x less memory than dict)
(github.com/kmike)
4 points
kmike84
14 years ago
discuss
649.
▲
Show HN: REPL is the memory layer for multi-agent AI apps – Sherlog‑MCP
(github.com/GetSherlog)
4 points
teenvan_1995
a year ago
discuss
650.
▲
Show HN: MemX – Shared memory for LLM agents
(github.com/MehulG)
4 points
mmmehulll
a year ago
discuss
651.
▲
Show HN: Quanta – A Fast, Memory-Efficient Data Engine for Analytics
(github.com/sagaripte)
4 points
sagari
a year ago
discuss
652.
▲
Show HN: I made an Neuroscience-Inspired Memory Layer for LLM Applications
(github.com/harishsg993010)
4 points
mrxhacker99
a year ago
discuss
653.
▲
The Fil-C Manifesto: Garbage In, Memory Safety Out
(github.com/pizlonator)
4 points
sibellavia
a year ago
discuss
654.
▲
Early draft discussion of memory regions for Go language to reduce GC overhead
(github.com/golang)
4 points
FZambia
2 years ago
discuss
655.
▲
jimfs: An in-memory file system for Java
(github.com/google)
4 points
mfiguiere
2 years ago
discuss
656.
▲
Metamalloc.h: Single header template based general purpose memory allocation
(github.com/akhin)
4 points
g0xA52A2A
2 years ago
discuss
657.
▲
Show HN: Fully Lock-Free Actor Model and Software Transactional Memory in C++20
(github.com/eduard-permyakov)
4 points
epermyakov
3 years ago
discuss
658.
▲
Griptape – a modular Python framework for LLM workflows, tools, memory, and data
(github.com/griptape-ai)
4 points
vapemaster
3 years ago
discuss
659.
▲
GPT3/DallE in Discord (updates), permanent memory done, auto-moderation, more
(github.com/Kav-K)
4 points
kaveenk
3 years ago
discuss
660.
▲
Pycopy: Minimalist and memory-efficient Python dialect
(github.com/pfalcon)
4 points
ingve
4 years ago
discuss
More