Feed aggregator

I built this because I was running 3-5 Claude Code instances on the same repo and burning out from constantly context switching between terminal windows. Carefully making sure agents' work didn't overlap, preventing context windows from degrading, manually enforcing documentation/memory policies, and re-explaining decisions across sessions.

Stoneforge is the coordination layer I wanted. A Director agent breaks goals into tasks. A dispatch daemon assigns them to workers when available, each task runs in its own git worktree. Stewards review completed tasks and squash-merge to main if everything passes inspection, otherwise they handoff the task with review comments to be picked up by a new agent. When a worker hits its context limit, it commits, writes handoff notes, and exits, so the next worker can pick up on the same branch with a fresh context window and important notes from the previous agent's work.

Some design decisions that might be interesting to this crowd:

- Fully event-sourced with a complete audit log. - Supports syncing tasks to Github or Linear, and documents to Notion, Obsidian, or a local folder. Custom providers are also supported. - JSONL as source of truth, SQLite as a disposable cache. JSONL diffs, merges across branches, and survives corruption. SQLite gives you FTS5 and indexed queries. The SQLite .db can be rebuilt on different devices in seconds. - No approval gates by default. If five agents each need confirmation for every file write, you won't be moving any faster. Review happens at the merge steward level. - Worktrees over containers. The conflict surface for coding agents is git and the file system, containers or remote instances are overkill. Worktrees create in milliseconds, share node_modules and build caches, and don't need Docker or separate servers. - You can run multiple Claude Code / Codex plans simultaneously on the same codebase.

Works with Claude Code, OpenAI Codex, and OpenCode. Apache 2.0. GitHub: https://github.com/stoneforge-ai/stoneforge

Happy to discuss the architecture or any of the tradeoffs.

Comments URL: https://news.ycombinator.com/item?id=47267105

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/shorts/CJrOMs4L-lc

Comments URL: https://news.ycombinator.com/item?id=47267099

Points: 1

# Comments: 1

Article URL: https://vault.fbi.gov/attempted-hacking-of-oldsmar-water-treatment-plant-on-february-5-2021/attempted-hacking-of-oldsmar-water-treatment-plant-on-february-5-2021-final/at_download/file

Comments URL: https://news.ycombinator.com/item?id=47267097

Points: 1

# Comments: 0

Article URL: https://www.macrumors.com/2026/03/05/mac-studio-no-512gb-ram-upgrade/

Comments URL: https://news.ycombinator.com/item?id=47267088

Points: 3

# Comments: 1

Article URL: https://twitter.com/im_roy_lee/status/2029606868369236088

Comments URL: https://news.ycombinator.com/item?id=47267073

Points: 1

# Comments: 0

Article URL: https://99helpers.com/tools/visual-contextual-chat

Comments URL: https://news.ycombinator.com/item?id=47267057

Points: 1

# Comments: 0

Article URL: https://melhorar-aprendizagem.com.br/

Comments URL: https://news.ycombinator.com/item?id=47267027

Points: 1

# Comments: 1

AI agents increasingly execute real system actions: issuing refunds, modifying databases, deploying infrastructure, calling external APIs.

Because agents retry steps, re-plan tasks, and run asynchronously, the same action can sometimes execute more than once.

In production systems this can cause duplicate payouts, repeated mutations, or inconsistent state.

Kybernis is a reliability layer that sits at the execution boundary of agent systems.

When an agent calls a tool:

1. execution intent is captured 2. the action is recorded in an execution ledger 3. idempotency guarantees are attached 4. the mutation commits exactly once

Retries become safe.

Kybernis is framework-neutral and works with agent frameworks like LangGraph, AutoGen, CrewAI, or custom systems.

I built this after repeatedly seeing reliability failures when AI agents interacted with production APIs.

Would love feedback from anyone building agent systems.

Comments URL: https://news.ycombinator.com/item?id=47267024

Points: 1

# Comments: 1

Article URL: https://economist.com/culture/2026/03/05/triumph-of-the-toons-how-animation-came-to-rule-the-box-office

Comments URL: https://news.ycombinator.com/item?id=47267022

Points: 1

# Comments: 0

Article URL: https://www.themarginalian.org/2026/03/05/alan-lightman-death/

Comments URL: https://news.ycombinator.com/item?id=47267007

Points: 2

# Comments: 0

Article URL: https://www.annualreviews.org/content/journals/10.1146/annurev-lawsocsci-111524-094646

Comments URL: https://news.ycombinator.com/item?id=47266997

Points: 2

# Comments: 1

Article URL: https://www.lableaks.dev/p/dereks-at-work

Comments URL: https://news.ycombinator.com/item?id=47266984

Points: 1

# Comments: 0

SafeAppeals is an AI-powered document workspace designed for legal professionals, researchers, injured workers, and anyone handling document-heavy workflows. Built with Electron and TypeScript, it combines a powerful code editor interface with native support for DOCX, PDF, Excel, and Markdown files.

Key features include: - Integrated AI agents powered by Claude, OpenAI, and Google APIs for document analysis and generation - Native document editing without conversion to plaintext - DocuSign integration for document signing workflows - Custom MCP (Model Context Protocol) server support - Flexible token-based pricing with BYOK option

Targeting the gap between general-purpose tools like Notion and Claude with document-specific AI workflows for professionals who need document integrity and AI assistance working together.

Comments URL: https://news.ycombinator.com/item?id=47266983

Points: 1

# Comments: 0

Article URL: https://github.com/jj-vcs/jj/releases/tag/v0.39.0

Comments URL: https://news.ycombinator.com/item?id=47266973

Points: 1

# Comments: 0

Soldier Boy, Homelander, Butcher and more appear in the season 5 preview.

Article URL: https://www.star-history.com/blog/ai-ui-irrelevant

Comments URL: https://news.ycombinator.com/item?id=47266944

Points: 1

# Comments: 0

just shipped vibe-auditor

npm i -g vibe-auditor auditor .

AI audits your entire codebase. finds what tests miss. delivers fixes you accept or reject in the terminal.

Comments URL: https://news.ycombinator.com/item?id=47266939

Points: 1

# Comments: 0

I played the new class, which lets you decide whether you want to stare into the abyss, drown your enemies in fire, summon legions of demons or just become one yourself.

Donald Trump said he would replace the secretary of the Department of Homeland Security. Noem's tenure was marked by aggressive anti-immigration tactics and ICE's killing of two US protestors.