AGENTS

→ View original post on X — @datachaz

Open-Source Claude Design Replica Runs Local With Multi-CLI Support

By

@datachaz

–

03 May 2026 23h22

Holy F*ck… someone just created an open-source replica of Claude Design Local-first. BYOK at every layer. Runs on whatever coding agent you already have on your laptop. The daemon scans your PATH for 13 different CLIs like Cursor, Gemini, Copilot, and Claude Code,

→ View original post on X — @saboo_shubham_

Google Agent Development Kit Features and Capabilities Overview

By

@saboo_shubham_

–

03 May 2026 21h55

Google Agent Development Kit is super underrated. I will look at:
– Agents CLI
– Ambient and Resume Agents
– Context Management
– Long term Memory
– Agent Evals (User and env simulation)

GPT-5.5 Impresses With Big Model Capability in Agent Harness Work

By

–

03 May 2026 21h52

A lot of that was harness work, had to redesign some ways OpenClaw does things, and yes GPT 5.5 has big model smell. It surprises you.

Crabbox 0.4.0 Ephemeral Machines for Agents on AWS Hetzner

By

–

03 May 2026 21h44

Crabbox 0.4.0. Often I need to quickly recreate conditions on macOS, Linux and Windows and need fast empheral machines. Crabbox are machines for agents on the fly, using AWS spot instances, Hetzner or @useblacksmith
. Infinite codex + tests! https://
crabbox.sh

Open Source AI Tooling for OSS Issue and PR Management

By

–

03 May 2026 21h26

This is the most useful tooling I built for OpenClaw to date. It's open source, runs on codex and you can fork and use it for any repo. For all the hard working oss folks that drown in issues and PRs, this is for you.

→ View original post on X — @reach_vb

Using Codex Agent to Hatch Pet from Reference Image

By

@reach_vb

–

03 May 2026 21h21

ask codex to /hatch pet based on this reference image

→ View original post on X — @reach_vb

Codex Security Plugin Ships Five AppSec Workflows for Repos

By

@reach_vb

–

03 May 2026 21h20

Team shipped a Codex Security plugin with 5 AppSec workflows: > Security Scan Scans PRs, commits, branches, patches, folders, or full repos. Runs the full pipeline end-to-end > Threat Model Maps the repo: assets, trust boundaries, attacker inputs, invariants, and failure

→ View original post on X — @databricks

Genie Agent Mode Enables Analyst-Style Data Exploration

By

@databricks

–

03 May 2026 20h10

Genie Agent Mode expands the class of questions you can ask of your data. Rather than returning a single query result, it works like a data analyst, planning an approach, testing hypotheses, and iterating toward a well-supported explanation.

Ask things like:
– Why did our churn… pic.twitter.com/nm87JiURwz
— Databricks (@databricks) 3 mai 2026

Genie Agent Mode expands the class of questions you can ask of your data. Rather than returning a single query result, it works like a data analyst, planning an approach, testing hypotheses, and iterating toward a well-supported explanation. Ask things like:
– Why did our churn

Codex Removes ACP Bridge for Direct App Server Integration

By

–

03 May 2026 20h05

codex doesn't support ACP so it uses a bridge, better is using the app server directly. Historically we supported acp and last few days I worked on removing that indirection.