» Tag
automation
201 postsNexFlow: Defining AI developer teams with YAML manifests
NexFlow defines AI agent teams through auditable YAML manifests instead of hidden prompts, separating capabilities from permissions to clarify approval gates.
Jean2: A Coding Agent That Evolves Across Sessions via File-Based Memory
Jean2 is a coding agent that writes what it learns into markdown files via opt-in memory, skill and session-search layers, improving through accumulated knowledge rather than model retraining.
The Right Amount of Specification for Agentic Development
An exploration of the importance and costs of the right amount of specification for agentic development.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comClick Issues with Claude in Chrome and Their Solutions
Explore click issues with Claude in Chrome, their two main causes, and solutions to improve automation reliability.
I put an API behind an x402 paywall for nine days: 1,835 callers, zero payments
longwatch API received 1,835 requests over nine days but zero payments. What does this mean for engineers?
Grabette: An Open System for Recording Robot Manipulation Data
Grabette is an open system for quickly recording robot manipulation data. Users can collect data easily with just a gripper.
The Missing Step Between Agents and Continual Learning
Liang Wenfeng discusses the interaction between agents and continual learning, focusing on the challenge of selecting trustworthy memories.
Nova: Open-Source AI Orchestrator to Manage Your Operations
Nova is an open-source AI orchestrator that manages operations with human approval.
Agentpause: Suspends LLM agents before rate limits, resumes cleanly
Agentpause allows LLM agents to suspend before hitting rate limits and resume seamlessly.
GitLab Packages Duo Agent Flows for Streamlined Multi-Step Runs
GitLab's Duo Agent Flows enhance multi-step run management, ensuring consistent access controls and security measures for delivery teams.