DR-Venus Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data paper: https://
huggingface.co/papers/2604.19
859
…
OPEN SOURCE
-
DR-Venus: Frontier Edge-Scale Deep Research Agents with 10K Data
By
–
-
OpenClaw: Open Source Self-Hosted AI Agent Management Platform
By
–
– Supports any model
— Robert Scoble (@Scobleizer) 23 avril 2026
– Self-hosted deployment, as low as €4/month
– Per-session sandbox environment
– Credential isolation
– Fully observable subagent (delegation)
It is MIT-licensed and open source. Give it a star on GitHub.
Link: https://t.co/kuQU56K2Yc https://t.co/wrk0Zl0w6F– Supports any model
– Self-hosted deployment, as low as €4/month
– Per-session sandbox environment
– Credential isolation
– Fully observable subagent (delegation) It is MIT-licensed and open source. Give it a star on GitHub. Link:
https://
github.com/stainlu/opencl
aw-managed-agents
… -
RLVR Effectiveness in Low Data Compute Regimes Study
By
–
Our MLSys 2026 paper is live on arXiv: “Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes.” @realjustinbauer @Walshe_tech @pham_derek @harit_v @ArminPCM @fredsala and @paroma_varma present a comprehensive empirical study of open-source SLMs
-
OpenClaw Distribution Through NPM Package Manager
By
–
nothing should run off homebrew, that has nothing to do with openclaw. we distribute via npm.
-
Open-sourced first Chrome extension SuperLevels on GitHub
By
–
✨ I open sourced my first Chrome extension 🚀 SuperLevelshttps://t.co/faWps9VAgE
— @levelsio (@levelsio) 23 avril 2026
I vibe coded it to replace all my Chrome extensions that are increasingly being bought up by spyware and malware companies who sell your data or worse hack your accounts and steal your… https://t.co/AmPtcIGz0A pic.twitter.com/sA6OSzS8XzI open sourced my first Chrome extension SuperLevels https://
github.com/levelsio/super
levels
… I vibe coded it to replace all my Chrome extensions that are increasingly being bought up by spyware and malware companies who sell your data or worse hack your accounts and steal your -
Hermes Agent: Open-Source Self-Improving AI Layer Everywhere
By
–
📣Hermes Agent just went from “cool dev toy” to everywhere AI layer.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 23 avril 2026
▪️ Open‑source, self‑improving agent from Nous Research — with persistent memory + auto‑generated skills that get better every time you run tasks.
▪️ New v0.9.0 “Everywhere” release: local web dashboard,… pic.twitter.com/Da1oS28Lw2Hermes Agent just went from “cool dev toy” to everywhere AI layer. Open‑source, self‑improving agent from Nous Research — with persistent memory + auto‑generated skills that get better every time you run tasks. New v0.9.0 “Everywhere” release: local web dashboard,
-
LLaDA2.0-Uni: Unified Multimodal Understanding and Generation with Diffusion
By
–
LLaDA2.0-Uni Unifying Multimodal Understanding and Generation with Diffusion Large Language Model paper: https://
huggingface.co/papers/2604.20
796
… -
GLM 5.1 Local Model Matches Opus 4.6 Performance
By
–
🚨 WE OFFICIALLY HAVE GLM 5.1 🚨
— Charly Wargnier (@DataChaz) 23 avril 2026
A local model as good as Opus 4.6 (in some evals), running right on a 256GB Mac Studio 🤯
WILD stats → 1,432 tokens / 1:17s / 18.47 t/s
..and it absolutely crushes SWE-Bench Pro!@BytePlusGlobal just bundled it with 5 other elite models 👀↓ https://t.co/cXK5Km54tS pic.twitter.com/2pTRXPge3sWE OFFICIALLY HAVE GLM 5.1 A local model as good as Opus 4.6 (in some evals), running right on a 256GB Mac Studio WILD stats → 1,432 tokens / 1:17s / 18.47 t/s ..and it absolutely crushes SWE-Bench Pro! @BytePlusGlobal just bundled it with 5 other elite models ↓
-
Google DESIGN.md: OSS spec for coding agents design systems
By
–
C'mon, way too reductive! Google’s DESIGN.md's an OSS spec for describing a design system to coding agents, with: > structured design tokens in YAML front matter
> human-readable design rationale in markdown
> a CLI that can lint, diff, export, and output the spec itself