Agora is a system that lets AI agents collaborate on research by storing all work as immutable Git commits in a directed acyclic graph, with a scoring system that rewards verified results. Researchers tested it with 13 language-model agents working to initialize a neural network without training, and they achieved 62% of the performance gap to a trained baseline in 12 days.

• Thirteen agents working independently with no central planner published 1,703 contributions over 12 days, with the best result closing 62% of the gap between random initialization (3.39 bpb) and a trained GPT-2 baseline (1.0 bpb).
• The winning approach used bigram statistics extracted from six donor models' predictions, factorized by SVD, plus sparse deterministic edits to sublayers—no gradient updates or training data involved.
• Early gains came fast: the first eight improvements accounted for roughly 70% of total progress, but agents converged into a monoculture around one recipe until shown a visualization of their own concentration.

East River Source Control is developing a new version control backend that speaks the Git protocol but replaces Git's storage layer to handle the demands of agentic development and massive monorepos. They're designing it to work with Jujutsu as a client, allowing teams to gradually migrate beyond Git's 2005-era constraints without abandoning existing tooling.

• Agentic AI development is creating problems at scale that previously only large companies faced: massive repositories, frequent branching, merge contention, and the need for fast cloud-based clones.
• Git was designed for the Linux kernel in 2005, not for billion-line monorepos or private enterprise features that modern organizations need, yet switching is risky because Git is embedded throughout the entire development ecosystem.
• ERSC's strategy is to keep the Git protocol as the client interface while replacing the backend storage engine, and eventually support Jujutsu as a client that can speak different protocols to enable a gradual migration path to future version control systems.

Orca lets you run multiple code-generation agents (Codex, ClaudeCode, Pi, etc.) side-by-side in isolated git worktrees and compare or merge their outputs. It combines split terminals, UI scraping, remote execution, commit workflows, and real-time mobile notifications to manage and steer agents without context switching.

• Orca runs multiple AI coding agents (Codex, ClaudeCode, OpenCode, Pi, etc.) in parallel using isolated git worktrees, so you can fan out one prompt to several agents and merge the best output.
• It bundles a full dev environment—WebGL terminal, embedded VS Code with autosave, and Chromium-based UI scraping to capture HTML/CSS/screenshots directly into prompts.
• Mobile apps (iOS/Android) let you get notified when agents finish or need input, then steer them, review PRs, and comment on diffs remotely.
• It's MIT-licensed and open source, installable via Homebrew, AUR, or prebuilt binaries, with every action scriptable via CLI commands.

This issue covers Cloudflare’s new real-time WAF rules, Anthropic’s Claude Fable and Mythos 5 models, and HashiCorp Boundary’s agent-aware access controls. It also highlights Microsoft Foundry’s model management, geo-distributed AI training with k0smos, plus tools like MemPalace, whichllm, a Rust Git rewrite, Kubernetes Inference Extension, and Cilium’s CI/CD hardening.

• Anthropic split Claude 5 into two tiers—Fable 5 for general use with a conservative safety layer, Mythos 5 with relaxed rails for vetted cyberdefense/life-sciences partners
• Mirantis and Logsight.ai used the open-source k0smos stack to pool Nvidia A100s in Quebec and AMD MI300Xs in Atlanta from Frankfurt, auto-scaling GPUs based on real-time electricity prices
• GitButler's Grit project rewrote Git in Rust using coding agents, passing 41,715 of 42,001 tests but burning 45 billion tokens and needing heavy human oversight
• MemPalace achieves 96.6% recall on LongMemEval by storing conversation memory as local text with no cloud calls

This issue covers practical tips for reading distributed traces, a deep dive into Git’s curious false_but_the_compiler_does_not_know_it_ variable, and why grep often outperforms semantic search. It also explores the shift to agent-focused development, the pitfalls of AI “rockstar” codebases, the AI industry’s financial crunch, and Apple’s moves to woo indie developers with cheaper and revamped AI services.

• Grep beats vector embeddings for long-memory QA tasks since exact matches catch dates and names that semantic search blurs.
• Git uses a global variable called false_but_the_compiler_does_not_know_it_ to suppress unreachable-code warnings without affecting link-time optimization.
• AI "rockstar" developers leave behind idiosyncratic code that AI tools will multiply into a mess without enforced architectural vision.
• The AI industry needs trillions in annual revenue by 2030 to cover compute debt, but spending growth is stalling as clients cut back, prompting Apple to offer free Private Cloud Compute access and a Gemini-powered Apple Intelligence revamp to court indie developers.

This article covers the `npx skills` CLI tool for installing, listing, updating, and removing reusable agent “skills” across over 40 coding agents. You can fetch skills from GitHub, GitLab, local paths, or any Git URL and target specific agents or install globally versus per-project.

• `npx skills` lets you install reusable "agent skills" from any GitHub/GitLab repo, local path, or Git URL into 40+ coding agents (Claude Code, Cursor, Codex, OpenCode, etc.)
• Supports fine-grained control: pick specific skills or whole repos, target specific agents, install globally vs per-project, and run non-interactively via --yes/--all for CI/CD
• Full lifecycle management is built in: list, find, update, remove, and init (to scaffold a new SKILL.md) for authoring your own skills
• Defaults to symlinking skills (single source of truth) but can copy files instead if symlinks aren't supported; community skills are browsable at skills.sh