TAG / OSS
OSS
Open code, and the people moving around it.
18 topics0 replies5 voices
The Agent Loop to Set Up Before Running 50 Claude Code Agents
Sanabi’s (@0xSanabi) post is about moving beyond one-off questions in Claude Code to a system where multiple agents work, check results, and move on. The first thing to emulate is a small loop with conditions for execution, verification, and stopping—not a 50-agent setup.
JetBrains ThinkRail: A Complete Workspace for AI Coding
ThinkRail is a lightweight IDE built around pi. It separates tasks with Git worktrees and takes you from chat to editing, review, and PRs using project specifications and skills.
【Definitive Guide】The Trust Behind 2,000 PRs a Month: Agent Design Lessons from Cursor’s Lauren Tan
Having AI agents write code only scales so far if people still review and fix every line. Lauren Tan’s approach focuses less on adding model instructions and more on building a development environment that prevents mistakes and lets agents verify their own work.
5 Patterns for Designing ADK Agent Skills
Skills need more than proper formatting to be effective. Choosing a design pattern that fits the task and defining how knowledge is loaded and work proceeds makes ADK agents more consistent.
Gartner’s 2027 Technology Trends: Three Shifts Businesses Should Prepare For
Gartner’s 2027 trends go beyond improving AI performance to address how to control autonomous agents and build IT environments that can adapt to change. Before rushing to adopt new technologies, businesses should decide where to use them and how to stop failures.
Prompt Design for Reliable Use of Claude Code
Rather than giving Claude Code detailed steps, clearly state what it must not do and how to verify its work. Including the reasons for restrictions and the scope of the task helps reduce unnecessary changes and unverified claims.
How Jev Changes AI Agent Harness Design
Jev makes it easier to separate small agent decisions from large LLMs and delegate them to code or specialized models. The design focus shifts from “which LLM to use” to “how to divide decisions and automate them safely.”
A Guide to “JevHarness · Pokémon Lab,” Where Jev Makes Pokémon Decisions
JevHarness · Pokémon Lab is a page for comparing actions written by an agent with options chosen by Jev in recorded Pokémon battles. The page does not run new battles or send model requests, so start by reviewing the playable recording and Jev’s responses.
Oracle’s Push for Autonomous Enterprise AI: What It Takes to Deliver Results
Oracle is seeking to move AI from reporting on conditions to executing tasks aligned with business goals. The focus of adoption is not the number of agents, but ensuring data access, business understanding, governance, and execution infrastructure are in place to deliver measurable results.
How to Read the Numbers Before Running a Large LLM Locally with Strata
Strata is an open-source tool that runs local LLMs on ordinary Windows, Linux, and Mac PCs and exposes OpenAI- and Anthropic-compatible APIs on localhost.
An Introduction to Jev-Mem for Controlling AI Agent Memory
Jev-Mem is an open-source memory framework that separates organizing and retrieving AI agent memories from reasoning about answers. The paper’s LoCoMo evaluation reports results that outperform the compared systems in both answer quality using GPT-4o-mini and retrieval speed.
How to Use Doubao Text-to-Speech in BytePlus LAS and Its Requirements
BytePlus LAS lets you call Volcano Engine's text-to-speech API from a Daft operator to convert text into audio data. Enterprise verification is required, so first check your verification status and API connection details.
Strands Decider 2B: A Small Model Built for Speed and Confidence
Strands Decider 2B is an open-source model with 2 billion parameters that selects answers from options instead of generating text. It runs on your own CPU or GPU, making it useful for testing low-latency decisions such as tool selection and input checks.
Getting Started with an AI-Native SDLC: A Practical Six-Stage Playbook
As AI shortens coding time, planning, review, testing, and releases determine how long development takes overall. This playbook focuses on adapting the SDLC for AI and establishing human decision points for each artifact.
Translating Meaning: Connecting Ontologies to Agent Actions
Organizing business rules into an ontology alone does not make agent decisions reliable. Business and technical teams need to identify and restore meaning lost when rules become execution conditions.
Run Your AI Agents in an “Office” with Munder Difflin
Munder Difflin is an open-source desktop app that runs terminal agents such as Claude Code and OpenAI Codex together. It suits people who want to distribute work across multiple agents using their existing CLIs and subscriptions.
Introduction to ripgrep: Search Code Quickly While Respecting .gitignore
ripgrep (`rg`) is a search tool that recursively searches directories while applying exclusion rules such as `.gitignore`. Start with `rg 'search term'`, and if some files are missing from the results, check the search filtering settings.
Can ai-memory hand off work from Claude Code to Codex?
ai-memory looks promising as long-term memory for passing the state of previous work to the next agent. However, handoff quality depends on summary quality, so you cannot judge its practicality until you try it on your own work.