grep -r "open source" /news · homesearch
grep -rli "open source" /news

open source

Full-text search across 20221 articles. Combine with topic and date filters; results sorted by relevance.

results 20221 page 115/1012
05:31
2026-07-08
davidbarnhart.com
large-language-models

Self-Hosting My Own LLMs

A user decided to self-host large language models in 2026 to maintain data sovereignty, privacy, and control over their conversations, using open-source tools and local hardware. The setup, built around an AMD Ryzen 9 59…

21:06
2026-06-19
simlink.snaz.cz
ai-agents

Show HN: Let agents send/receive SMS using your old Android phone

SimLink by Snáz.cz is an open-source, self-hostable server that gives AI agents a real phone number by relaying SMS through an old Android phone and a prepaid SIM card via the Model Context Protocol. The service encrypts…

10:47
2026-08-01
lancedb.com
artificial-intelligence

Semantic Memory for Hermes Agent with LanceDB

Nous Research's open-source Hermes Agent now supports a LanceDB memory plugin that adds semantic, long-term recall across sessions, addressing the agent's tendency to forget user preferences and facts. The plugin impleme…

20:25
2026-08-14
theregister.com
ai-tools

DeepSeek's innovative harness treats everything as a plug-in

DeepSeek released an early version of its open source agent harness, DeepSeek Harness, built on the Cordis meta-framework, which treats models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and U…

15:08
2026-08-09
sourcefeed.dev
artificial-intelligence

Voice AI's Hard Problems Moved Into the Framework Layer

LiveKit Agents, the open-source framework from LiveKit that powers ChatGPT's voice mode and counts xAI, Salesforce, and 911 dispatch operators among its customers, is trending on GitHub as developers adopt its production…

05:12
2026-07-07
maestro.dev
ai-tools

Maestro: Agentic Mobile UI Testing

Mobile Dev Inc. released Maestro, an open-source, AI-native mobile UI testing tool that enables agentic velocity with human-readable YAML tests and easy CI integration. The tool, battle-tested and time-tested, allows dev…

08:21
2026-06-24
maref.cc
artificial-intelligence

GitHub Is Becoming a Giant AI Code Dump

GitHub has 630 million repositories, with nearly half of all new code written by AI, but developer trust in AI code dropped from 77% to 60%. Carnegie Mellon University found 6 million fake stars, and CodeRabbit reported …

18:02
2026-08-03
dev.to
artificial-intelligence

Best Vector Databases for AI Applications in 2026

A new ranking of vector databases for AI applications in 2026 highlights Pinecone, Weaviate, Milvus, and pgvector as top choices, evaluated on performance, scalability, ease of use, and enterprise readiness. The analysis…

10:32
2026-06-17
infoworld.com
large-language-models

Z.ai pitches GLM-5.2 for long-running software engineering tasks

Z.ai released GLM-5.2, an MIT-licensed open-source AI model for long-running software engineering tasks, claiming it trails Anthropic's Claude Opus 4.8 by 1% on the FrontierSWE benchmark and edges out OpenAI's GPT-5.5 by…

19:32
2026-07-20
cryptobriefing.com
artificial-intelligence

Moonshot’s Kimi K3 model aims to help China challenge US AI dominance

Beijing-based startup Moonshot AI has unveiled Kimi K3, a 2.8 trillion parameter model using mixture-of-experts architecture, claiming it outperforms Anthropic's Claude Opus 4.8 and OpenAI's GPT-5.5 on coding and long-ho…

06:12
2026-06-09
latent.space
artificial-intelligence

[AINews] FrontierCode: Benchmarking for Code Quality over Slop

Cognition introduced FrontierCode, a new benchmark that evaluates code on mergeability rather than just unit-test passing, with tasks built by open-source maintainers requiring over 40 hours each. The best model, Opus 4.…

08:18
2026-06-29
blog.alexewerlof.com
ai-tools

Linkedout: See how much data LinkedIn has on you

Developer Alex Ewerlöf created LinkedOut, a free open-source Chrome extension that reveals the extensive data LinkedIn collects on users, including 54,000 data points from his 16-year account history. The app allows user…

23:16
2026-06-12
letsdatascience.com
large-language-models

Xiaomi MiMo Hits 1,000 Tokens-Per-Second Inference

Xiaomi's MiMo-V2.5-Pro-UltraSpeed, a 1.02-trillion-parameter MoE model, achieved 1,000 tokens per second inference on standard cloud GPUs using FP4 quantization, DFlash speculative decoding, and TileRT runtime. The miles…

22:56
2026-07-28
thenextweb.com
artificial-intelligence

China’s free AI models may not stay free, Goldman says

Chinese AI developers may start charging cloud platforms commercial licensing fees to host their open-weight models, Goldman Sachs told the South China Morning Post, a shift that could alter the economics of China's free…

13:00
2026-08-11
research.ibm.com
artificial-intelligence

From vision to reality: a unified AI solver for the grid

IBM Research and partners released GENCO, an open-source neural solver that unifies three steady-state grid-analysis tasks, alongside the GridFM Development Framework under Linux Foundation Energy's OpenGridFM project. T…

22:33
2026-07-03
mistral.ai
artificial-intelligence

Leanstral 1.5: Proof Abundance for All

Leanstral 1.5, a free Apache-2.0 licensed model with 6B active parameters, delivers major performance upgrades in formal verification, saturating miniF2F, solving 587/672 PutnamBench problems, and achieving state-of-the-…

13:27
2026-06-27
byteiota.com
large-language-models

DeepSeek DSpark Goes Live with 80% Inference Speed Gains

DeepSeek released DSpark, a speculative decoding framework now live in its DeepSeek-V4 Flash and Pro production API, delivering 51 to 400 percent throughput gains and up to 80 percent latency reduction over standard auto…

← prev page 115 / 1012 next →