cd/sources/michielbdejong-auto-discovered· home› sources› Michielbdejong (auto-discovered)
cat /sources/michielbdejong-auto-discovered.feed | wc -l → 5082

Michielbdejong (auto-discovered)

articles 5082 domain github.com → page 59/255 feed RSS
05:36
2026-08-29
github.com
developer-tools

LaneGate – Git-native worktree orchestrator for AI agents

LaneGate, a new open-source git-native worktree orchestrator, coordinates AI coding agents like Claude, Codex, Ollama, and aider by giving each ticket its own git worktree, enforcing file-level locks,…

03:12
2026-08-29
github.com
developer-tools

rules for ai agents

A developer published a set of mandatory coding guidelines for AI agent development, emphasizing branch management, code quality principles, and syntax verification. The rules require contributors to …

02:35
2026-08-29
github.com
ai-agents

Subs, a cloud native agent harness

Substructure AI released Subs, a pre-1.0 cloud-native agent harness that runs an unprivileged agent loop with no system access, using MCP servers for tools and supporting local or client-server operat…

23:55
2026-08-28
github.com
ai-tools

Quanta.Ai.Code.Editor

Quanta, a local-first AI code editor built on VS Code OSS with a Rust backend, has been released, offering agentic coding powered primarily by local LLMs via Ollama, with optional cloud backends. The …

22:33
2026-08-28
github.com
ai-agents

ai-agent-skills-workflows-index.md

A developer has released a collection of GitHub repositories indexing resources on agentic AI skills, Claude architectures, and terminal developer workflows. The repositories include implementation pa…

21:23
2026-08-28
github.com
developer-tools

slop function

A developer shared a systemd-based tool called 'slop' that caps memory usage for resource-hungry applications like VS Code and Claude. The tool uses a systemd slice with memory limits and a shell func…

20:40
2026-08-28
github.com
large-language-models

Tencent Hy4 Preview LLM

Tencent's Hy Team released Hy4 preview, a 770B-parameter Mixture-of-Experts flagship model with 49B activated parameters per token, featuring Gated DeepSeek Sparse Attention and a 1M context length. T…

← prev page 59 / 255 next →