qdrddr.bsky.social
@qdrddr.bsky.social
OpenClaw - Mem0
docs.mem0.ai
February 6, 2026 at 2:50 PM
𝗸𝘂𝗯𝗲𝗰𝘁𝗹-𝗸𝗲𝘆𝗰𝗵𝗮𝗶𝗻: A lightweight #GitOps utility that stores private certificates from your #Kubernetes config in the #macOS #Keychain instead of keeping them in plain text. Move your certificates in simple 3 steps.
MIT lic
#OpenSource #k8s #Security

github.com/qdrddr/kubec...
GitHub - qdrddr/kubectl-keychain
Contribute to qdrddr/kubectl-keychain development by creating an account on GitHub.
github.com
February 5, 2026 at 8:19 PM
February 5, 2026 at 1:41 AM
@apache.org AGE extension for #PostgreSQL18: native #GraphDB in #SQL 🗄️🕸️
Mix SQL + #Cypher → no external graph stack
🧩 Hybrid queries
📊 Fast indexing
🔌 Multi-SDK
📜 Apache 2.0 lic

#AI #RAG #OpenSource #GraphRAG #Graph
Repost 🔁 🔗 Link in first 💬⤵️
February 5, 2026 at 1:32 AM
GLiNKER - #EntityLinking Framework by Knowledgator
transforms raw text into structured, disambiguated entity mentions. Built around #GLiNER - a family of lightweight, generalist models for information extraction.
#Graph #GraphRAG #RAG #AI #LLM #SLM #NER
Apache 2.0 lic

github.com/Knowledgator...
GitHub - Knowledgator/GLinker: Efficient and scalable zero-shot entity linking
Efficient and scalable zero-shot entity linking . Contribute to Knowledgator/GLinker development by creating an account on GitHub.
github.com
February 3, 2026 at 5:07 PM
Reposted
☝️ I have seen tons of tools, tons.... but for a veeeeeery loooooong time, this one here is a #devops heaven, this is the lamborghini when it comes to managing cron jobs, it´s amazing 😍 🚀 ⭐ 🏎️

🔗 github.com/pixlcore/xyops

thanks mastodon.social/@jhuckaby (author) for this amazing project 🙏

#linux
February 1, 2026 at 10:43 AM
OGRAG by #Microsoft
#RDF #GraphRAG with hypergraphs to incorporate #ontology grounded knowledge.
MIT license
#OpenSource #GraphDB #RAG #AI #LLM
Link in the first comment💬👇
January 31, 2026 at 3:26 PM
Now you can integrate #Microsoft #Copilot #CodingAgent via SDK into your app.
Java, .NET/C#, Python, TypeScript, Go bindings
MIT license
#OpenSource #AI #Agents #LLM #Coding
github.com/github/copil...
GitHub - github/copilot-sdk: Multi-platform SDK for integrating GitHub Copilot Agent into apps and services
Multi-platform SDK for integrating GitHub Copilot Agent into apps and services - github/copilot-sdk
github.com
January 28, 2026 at 3:20 PM
DeepSpeed.ai: #PyTorch optimization for #LLMs
🧠 Memory dedup → train & infer models faster
🔌 Multi-framework 🧩 #NVIDIA + #AMD
🐍 Python
📜 Apache 2.0

#AI #OpenSource Repost 🔁
🔗 Link in first 💬⤵️
January 26, 2026 at 8:31 PM
TuringDB #inmemory #graphDB
OpenCore #opensource. 0.1-50ms query latency for analytical queries on 10M+ node graphs:
- parallelism & no read/write locks
- git-like versioning
- C++ & Python SDK bindings or container
- OpenCypher
BSL license
#Cypher #KnowledgeGraph #LPG #AI
Link in first 💬 👇
January 26, 2026 at 7:58 PM
Popular #DeBERTa model gets updated with FlashAttention by Knowledgator

🔹2–5× efficiency gains compared to the torch implementation of DeBERTa
🔹Lower memory footprint
🔹Support of backward
Apache 2.0 lic

#BERT #AI #SLM #LLM #OpenSource
github.com/Knowledgator...
GitHub - Knowledgator/FlashDeBERTa: Trully flash implementation of DeBERTa disentangled attention mechanism.
Trully flash implementation of DeBERTa disentangled attention mechanism. - Knowledgator/FlashDeBERTa
github.com
January 26, 2026 at 7:43 PM
2026 #AI Outlook: From #VibeCoding to #NeuroSymbolic Systems — 15 practical #Predictions for the next 12-18 months for builder’s & business by Damien Berezenko: pub.towardsai.net/2026-ai-outl...
January 25, 2026 at 4:56 PM
SemHash - a lightweight Semantic #Dedup & Filters
MIT lic
#AI #ML #OpenSource

github.com/MinishLab/se...
GitHub - MinishLab/semhash: Fast Multimodal Semantic Deduplication & Filtering
Fast Multimodal Semantic Deduplication & Filtering - MinishLab/semhash
github.com
January 19, 2026 at 2:07 PM
AutoMem a #Graph Vector #memory
Based on HippoRAG and others. #SOTA on #LoCoMo benchmark - scored 90.53% and 100% on multi-step complex reasoning. #MCP server available.
#AI #LLM #Agents #OpenSource
MIT lic

github.com/verygoodplug...
GitHub - verygoodplugins/automem: AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory: - verygoodplugins/automem
github.com
January 19, 2026 at 1:58 PM
Google Translate #opensource small language models
Designed for edge computing
Gemma License
#AI #LLM #SLM

huggingface.co/collections/...
TranslateGemma - a google Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 16, 2026 at 6:04 PM
Adaptive routing across #LLM 🤖⚖️
Route by cost, latency & task complexity → less compute, same quality
🧠 Learned/heuristic decisions
🛠️ Ops-ready
📜 MIT lic

#AI #RAG #OpenSource Repost 🔁
🔗 Link in first 💬⤵️
January 13, 2026 at 11:11 PM
Remote debugger for #Python 3.14 apps
by @savannah.dev
A zero-preparation remote debugger, no code changes or restarts required
Full breakpoint debugging - Using debugpy. Interactive process picker.

Useful with #containers and #Kubernetes.
MIT lic

#OpenSource #DevOps
github.com/savannahostr...
GitHub - savannahostrowski/debugwand: An *experimental* zero-preparation remote debugger for Python applications running in *local* Kubernetes clusters or Docker containers.
An *experimental* zero-preparation remote debugger for Python applications running in *local* Kubernetes clusters or Docker containers. - savannahostrowski/debugwand
github.com
January 10, 2026 at 7:25 PM
KGGen: Chunking, Clustering, #KnowledgeGraph generation, aggregating multiple graphs.
Available via Python bindings or as an #MCP Server.
MIT lic
#AI #RAG #Agents #OpenSource
github.com/stair-lab/kg...
GitHub - stair-lab/kg-gen: [NeurIPS '25] Knowledge Graph Generation from Any Text
[NeurIPS '25] Knowledge Graph Generation from Any Text - stair-lab/kg-gen
github.com
January 10, 2026 at 6:40 PM
@mozilla.ai MCPD #proxy with plugin system - Enterprise Context Management with #AuthZ / #AuthN, #Observability, #Audit, Rate Limiting. Validates request/response structure. Transforms Content Payload. Apache 2.0 lic
#MCP #ContextEngineering #AI #LLM #OpenSource
Link in 💬👇
January 10, 2026 at 1:10 PM