References & Resources — Agentic Software Factory (machine copy)

Gotcha for agents: the bare agent.md URL serves here.now's HTML viewer. Fetch agent.md?raw to get this file as plain text.

What this file is: every tool category the workshop-2026-07-17 demos use, with the tool John uses and vetted alternatives — one line per alternative (name — URL — what it is; stars/last-push/license retrieved 2026-07-17 via the GitHub API). No endorsements. Use it to map the workshop's patterns onto a user's constraints (OS, license policy, budget, install rules).

How to use: ask your user which constraints apply, then for each category they can't adopt John's tool, pick the alternative whose "what it is" line fits. "NOASSERTION" license = custom/source-available; check the repo's LICENSE before commercial adoption.

Categories

Terminal coding agents

John uses: pi (plus Codex CLI, Claude Code, Grok CLI) — https://github.com/earendil-works/pi (71,937 stars, MIT, pushed 2026-07-16); Codex: https://github.com/openai/codex; Claude Code: https://github.com/anthropics/claude-code; Grok Build: https://x.ai/cli

Terminal workspace / agent multiplexers

John uses: Herdr — https://herdr.dev/ — https://github.com/ogulcancelik/herdr (17,305 stars, AGPL-3.0 per herdr.dev, pushed 2026-07-17)

Terminal emulators

John uses: Ghostty — https://github.com/ghostty-org/ghostty (58,291 stars, MIT, pushed 2026-07-17)

AI context bundlers (repo → prompt)

John uses: packx — npm: npm install -g packx (johnlindquist); related: https://github.com/johnlindquist/pack (smart file filter for Repomix)

Prompt composing / prompt tooling

John uses: prompt-builder (p) — https://github.com/johnlindquist/prompt-builder (MIT, pushed 2026-07-17; ~/dev/prompt-builder locally, p alias)

Markdown agent flows / executable prompts

John uses: mdflow (md) — https://github.com/johnlindquist/mdflow (597 stars, MIT, pushed 2026-07-16; ~/dev/mdflow)

Browser automation for agents

John uses: Oracle (John's fork) + agent-browser — Oracle fork: https://github.com/johnlindquist/oracle (~/dev/oracle); agent-browser: https://github.com/vercel-labs/agent-browser (38,627 stars, Apache-2.0, pushed 2026-07-16)

Instant web publishing for agents

John uses: here.now — https://here.now/ (commercial service; skill-based agent integration, no sign-up required for anonymous sites)

Screenshot capture & annotation

John uses: CleanShot X — https://cleanshot.com/ (paid, macOS only)

Agent conversation search / memory

John uses: cs (conversation search CLI) — personal/unreleased (referenced throughout the workshop docs)

Preference capture / personal RLHF

John uses: this-or-that kit — https://gentle-lasso-9d5n.here.now/ (kit files published at /kit/); repo section 10-this-or-that; also an mdflow flow and an agent skill

Keyboard customization / hotkey layers

John uses: Karabiner-Elements + Goku (karabiner.edn) — https://github.com/pqrs-org/Karabiner-Elements (22,491 stars, Unlicense, pushed 2026-07-16); Goku: https://github.com/yqrashawn/GokuRakuJoudo (1,407 stars, GPL-3.0, last push 2025-08-15)

Secrets management for agent workflows

John uses: 1Password op CLI — https://developer.1password.com/docs/cli/ (commercial, subscription)

Agent skills: authoring & distribution

John uses: skills CLI (skills.sh) + ~/.agents/skills — https://github.com/vercel-labs/skills (26,358 stars, pushed 2026-07-16)

Just-in-time app state capture (markers)

John uses: agent-markers (09-markers demo) — workshop repo 09-markers/demo/agent-markers.js; published pattern at https://mindful-mango-accy.here.now/

Image generation for design variations

John uses: Codex $imagegen skill + agy (Google Antigravity CLI) — Codex: https://github.com/openai/codex; Antigravity CLI: https://github.com/google-antigravity/antigravity-cli (1,615 stars, pushed 2026-07-16)

Unverifiable / flagged

Also mentioned (no table needed)

Human-facing page: https://dewy-sleet-n5zs.here.now/ — tables with the same data plus "pick this if…" fit guidance per category.

# References & Resources — Agentic Software Factory (machine copy)

> Gotcha for agents: the bare `agent.md` URL serves here.now's HTML viewer. Fetch `agent.md?raw` to get this file as plain text.

What this file is: every tool category the workshop-2026-07-17 demos use, with the tool John uses and vetted alternatives — one line per alternative (name — URL — what it is; stars/last-push/license retrieved 2026-07-17 via the GitHub API). No endorsements. Use it to map the workshop's patterns onto a user's constraints (OS, license policy, budget, install rules).

How to use: ask your user which constraints apply, then for each category they can't adopt John's tool, pick the alternative whose "what it is" line fits. "NOASSERTION" license = custom/source-available; check the repo's LICENSE before commercial adoption.

## Categories

### Terminal coding agents
John uses: pi (plus Codex CLI, Claude Code, Grok CLI) — https://github.com/earendil-works/pi (71,937 stars, MIT, pushed 2026-07-16); Codex: https://github.com/openai/codex; Claude Code: https://github.com/anthropics/claude-code; Grok Build: https://x.ai/cli
- OpenCode — https://github.com/anomalyco/opencode — Open-source terminal coding agent, provider-agnostic (any model) (186,658★, 2026-07-17, MIT)
- Gemini CLI — https://github.com/google-gemini/gemini-cli — Google's open-source terminal agent for Gemini models (106,024★, 2026-07-16, Apache-2.0)
- Goose — https://github.com/aaif-goose/goose — Extensible AI agent (Block) that installs, executes, edits, and tests with any LLM (51,211★, 2026-07-17, Apache-2.0)
- Aider — https://github.com/Aider-AI/aider — AI pair programming in your terminal; git-native diff/commit workflow (47,447★, 2026-05-22, Apache-2.0)
- Crush — https://github.com/charmbracelet/crush — Charm's glamorous terminal coding agent (successor to OpenCode's original TUI) (26,569★, 2026-07-17, NOASSERTION)
- OpenHands — https://github.com/OpenHands/OpenHands — AI-driven development platform (formerly OpenDevin) with CLI, GUI, and cloud runtimes (81,045★, 2026-07-17, NOASSERTION)
- Grok Build (official) / superagent-ai grok-cli (OSS) — https://x.ai/cli and https://github.com/superagent-ai/grok-cli — xAI's official terminal coding agent (subscription); an OSS coding agent for the Grok API (3,291★, 2026-07-06, MIT (OSS one); Grok Build is proprietary)

### Terminal workspace / agent multiplexers
John uses: Herdr — https://herdr.dev/ — https://github.com/ogulcancelik/herdr (17,305 stars, AGPL-3.0 per herdr.dev, pushed 2026-07-17)
- tmux — https://github.com/tmux/tmux — The standard terminal multiplexer (47,852★, 2026-07-16, ISC)
- Zellij — https://github.com/zellij-org/zellij — Terminal workspace with batteries included (layouts, plugins in WASM) (34,330★, 2026-07-10, MIT)
- claude-squad — https://github.com/smtg-ai/claude-squad — Manage multiple AI terminal agents (Claude Code, Codex, OpenCode, Amp) in one TUI (8,131★, 2026-06-17, AGPL-3.0)
- Vibe Kanban — https://github.com/BloopAI/vibe-kanban — Kanban web UI for orchestrating multiple coding-agent tasks (27,405★, 2026-04-24, Apache-2.0)
- hcom — https://github.com/aannoo/hcom — Lets AI agents message, watch, and spawn each other across terminals (Claude Code, Codex, Antigravity, Pi, ...) (385★, 2026-07-07, MIT)
- Omnara — https://github.com/omnara-ai/omnara — Talk to your AI agents from anywhere (mobile/web control plane, YC S25) (2,650★, 2026-01-19, Apache-2.0)

### Terminal emulators
John uses: Ghostty — https://github.com/ghostty-org/ghostty (58,291 stars, MIT, pushed 2026-07-17)
- WezTerm — https://github.com/wezterm/wezterm — GPU-accelerated cross-platform terminal emulator AND multiplexer in Rust, Lua-configurable (27,636★, 2026-07-16, NOASSERTION (MIT per repo))
- kitty — https://github.com/kovidgoyal/kitty — Fast, feature-rich GPU-based terminal with 'kittens' extensions and remote control protocol (33,913★, 2026-07-16, GPL-3.0)
- Alacritty — https://github.com/alacritty/alacritty — Minimal, very fast OpenGL terminal emulator (64,935★, 2026-07-14, Apache-2.0)
- iTerm2 — https://github.com/gnachman/iTerm2 — The long-standing macOS power-user terminal (Python scripting API, triggers, tmux integration) (17,830★, 2026-07-17, GPL-2.0)

### AI context bundlers (repo → prompt)
John uses: packx — npm: `npm install -g packx` (johnlindquist); related: https://github.com/johnlindquist/pack (smart file filter for Repomix)
- Repomix — https://github.com/yamadashy/repomix — Packs an entire repository into a single AI-friendly file (XML/MD), with token counts and remote-repo support (27,172★, 2026-07-15, MIT)
- gitingest — https://github.com/coderamp-labs/gitingest — Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract (15,133★, 2026-07-14, MIT)
- code2prompt — https://github.com/mufeedvh/code2prompt — Rust CLI: codebase → single prompt with source tree, Handlebars templating, token counting (7,479★, 2026-06-29, MIT)
- files-to-prompt — https://github.com/simonw/files-to-prompt — Simon Willison's minimal concatenator: directory → one prompt (pairs with his `llm` CLI) (2,756★, 2025-02-19, Apache-2.0)
- yek — https://github.com/mohsen1/yek — Fast Rust serializer for repo files, chunks by token budget, priority-orders files (2,465★, 2026-06-29, MIT)

### Prompt composing / prompt tooling
John uses: prompt-builder (`p`) — https://github.com/johnlindquist/prompt-builder (MIT, pushed 2026-07-17; ~/dev/prompt-builder locally, `p` alias)
- fabric — https://github.com/danielmiessler/Fabric — Open-source framework with a crowdsourced library of reusable AI prompts ('patterns') runnable from the CLI (43,106★, 2026-07-16, MIT)
- llm (Simon Willison) — https://github.com/simonw/llm — CLI for any LLM with reusable templates, fragments, logged history in SQLite (12,194★, 2026-07-09, Apache-2.0)
- aichat — https://github.com/sigoden/aichat — All-in-one LLM CLI: Shell Assistant, chat REPL, roles, sessions, RAG, macros (10,248★, 2026-02-23, Apache-2.0)
- espanso — https://github.com/espanso/espanso — Privacy-first cross-platform text expander in Rust (14,107★, 2026-07-12, GPL-3.0)
- promptfoo — https://github.com/promptfoo/promptfoo — Test/eval harness for prompts, agents, and RAGs with declarative configs (23,343★, 2026-07-17, MIT)

### Markdown agent flows / executable prompts
John uses: mdflow (`md`) — https://github.com/johnlindquist/mdflow (597 stars, MIT, pushed 2026-07-16; ~/dev/mdflow)
- Claude Code slash commands & skills (built-in) — https://docs.claude.com/en/docs/claude-code — Markdown files in .claude/commands and .claude/skills that become reusable parameterized agent behaviors (stars n/a, push n/a, product docs)
- dotprompt — https://github.com/google/dotprompt — Google's executable GenAI prompt template format (.prompt files: frontmatter + template) (549★, 2026-07-10, Apache-2.0)
- BAML — https://github.com/BoundaryML/baml — A programming language for agents/prompts with typed inputs/outputs and tests (8,560★, 2026-07-17, Apache-2.0)
- fabric patterns — https://github.com/danielmiessler/Fabric — Markdown prompt 'patterns' executed via the fabric CLI against any model (43,106★, 2026-07-16, MIT)
- llm templates — https://github.com/simonw/llm — YAML templates with params for the llm CLI (12,194★, 2026-07-09, Apache-2.0)

### Browser automation for agents
John uses: Oracle (John's fork) + agent-browser — Oracle fork: https://github.com/johnlindquist/oracle (~/dev/oracle); agent-browser: https://github.com/vercel-labs/agent-browser (38,627 stars, Apache-2.0, pushed 2026-07-16)
- browser-use — https://github.com/browser-use/browser-use — Python library making websites accessible to AI agents; can attach to your real Chrome profile (105,135★, 2026-07-17, MIT)
- Playwright MCP — https://github.com/microsoft/playwright-mcp — Microsoft's MCP server exposing Playwright browser control to any MCP-capable agent (35,184★, 2026-07-15, Apache-2.0)
- Stagehand — https://github.com/browserbase/stagehand — SDK for browser agents (act/extract/observe primitives on Playwright, by Browserbase) (23,535★, 2026-07-16, MIT)
- Skyvern — https://github.com/Skyvern-AI/skyvern — Automate browser workflows with LLMs + computer vision (22,453★, 2026-07-17, AGPL-3.0)
- nanobrowser — https://github.com/nanobrowser/nanobrowser — Chrome extension for multi-agent web automation with your own API keys (13,473★, 2025-11-24, Apache-2.0)
Note: Oracle's specific niche — riding subscription cookies into ChatGPT/Gemini web UIs for max-intelligence consults and video understanding — has no direct maintained OSS equivalent we could verify. The honest substitutes are (a) the tools above to rebuild the pattern, or (b) paying for API access: Gemini API/Gemini CLI for video understanding, ChatGPT Pro via Codex CLI for deep reasoning.

### Instant web publishing for agents
John uses: here.now — https://here.now/ (commercial service; skill-based agent integration, no sign-up required for anonymous sites)
- surge.sh — https://github.com/sintaxi/surge — CLI for publishing static sites to the surge.sh CDN in one command (3,044★, 2026-07-13, none listed)
- Cloudflare Pages (wrangler) — https://github.com/cloudflare/workers-sdk — wrangler CLI deploys static sites/functions to Cloudflare's edge (John's inspiration-board uses it) (4,338★, 2026-07-17, Apache-2.0)
- Vercel — https://github.com/vercel/vercel — `vercel deploy` for static or full-stack sites with preview URLs (15,929★, 2026-07-17, Apache-2.0)
- GitHub Pages — https://pages.github.com/ — Free static hosting from a repo branch (stars n/a, push n/a, product)
- Netlify Drop — https://app.netlify.com/drop — Drag-and-drop a folder, get a live URL (stars n/a, push n/a, product)
Note: here.now's agent-first combination (skill-driven publish + private agent Drives + no-signup anonymous sites) is fairly unique; the entries above cover the static-publish half only.

### Screenshot capture & annotation
John uses: CleanShot X — https://cleanshot.com/ (paid, macOS only)
- Shottr — https://shottr.cc/ — Fast, lightweight macOS screenshot tool: annotate, scrolling capture, OCR, ruler, color picker (stars n/a, push n/a, freeware/paid (closed source))
- Flameshot — https://github.com/flameshot-org/flameshot — Cross-platform OSS screenshot software with in-place arrow/text annotation (30,398★, 2026-07-11, GPL-3.0)
- ksnip — https://github.com/ksnip/ksnip — Cross-platform screenshot and annotation tool (Qt) (3,257★, 2026-07-03, GPL-3.0)
- macOS built-in Screenshot + Preview markup — https://support.apple.com/guide/mac-help/take-screenshots-or-screen-recordings-mh26782/mac — Cmd+Shift+5 capture, then Markup arrows in Preview/Quick Look (stars n/a, push n/a, OS built-in)
- Kap — https://github.com/wulkano/Kap — OSS macOS screen recorder (GIF/MP4) (19,282★, 2024-11-12, MIT)

### Agent conversation search / memory
John uses: cs (conversation search CLI) — personal/unreleased (referenced throughout the workshop docs)
- cc-sessions-viewer — https://github.com/jerrywu001/cc-sessions-viewer — Viewer for Claude Code/Codex/Antigravity/OpenCode sessions: global search, token stats, resume, HTML export (242★, 2026-07-16, none listed)
- claude-conversation-extractor — https://github.com/ZeroSumQuant/claude-conversation-extractor — Extract clean conversation logs from Claude Code's internal storage (645★, 2026-01-02, MIT)
- llm logs (Simon Willison) — https://github.com/simonw/llm — Every llm CLI prompt/response logged to SQLite; `llm logs -q` full-text search (12,194★, 2026-07-09, Apache-2.0)
- ripgrep over ~/.claude/projects and ~/.codex/sessions — https://github.com/BurntSushi/ripgrep — Both Claude Code and Codex store sessions as local JSONL — rg searches them directly (stars n/a, push n/a, MIT/Unlicense)
- ccusage — https://github.com/ccusage/ccusage — npx ccusage — analytics over Claude Code local session data (17,221★, 2026-07-17, NOASSERTION)

### Preference capture / personal RLHF
John uses: this-or-that kit — https://gentle-lasso-9d5n.here.now/ (kit files published at /kit/); repo section 10-this-or-that; also an mdflow flow and an agent skill
- FastChat (Chatbot Arena) — https://github.com/lm-sys/FastChat — The platform behind Chatbot Arena: side-by-side battles + Elo ratings for LLM outputs (39,490★, 2026-05-01, Apache-2.0)
- Argilla — https://github.com/argilla-io/argilla — Collaboration tool for building high-quality AI datasets, including preference/ranking records (5,038★, 2026-07-13, Apache-2.0)
- Label Studio — https://github.com/HumanSignal/label-studio — Multi-type data labeling tool with pairwise-comparison templates (27,854★, 2026-07-17, Apache-2.0)
- potato — https://github.com/davidjurgens/potato — Portable academic annotation tool (Python), supports pairwise/best-worst schemes (397★, 2026-07-15, GPL-3.0)
- promptfoo — https://github.com/promptfoo/promptfoo — Prompt/agent eval harness with side-by-side output comparison views (23,343★, 2026-07-17, MIT)

### Keyboard customization / hotkey layers
John uses: Karabiner-Elements + Goku (karabiner.edn) — https://github.com/pqrs-org/Karabiner-Elements (22,491 stars, Unlicense, pushed 2026-07-16); Goku: https://github.com/yqrashawn/GokuRakuJoudo (1,407 stars, GPL-3.0, last push 2025-08-15)
- kanata — https://github.com/jtroo/kanata — Cross-platform advanced keyboard remapper (layers, tap-hold) in Rust (7,629★, 2026-07-15, LGPL-3.0)
- kmonad — https://github.com/kmonad/kmonad — Advanced keyboard manager (Haskell), layers and macros, cross-platform (5,031★, 2026-06-15, MIT)
- Hammerspoon — https://github.com/Hammerspoon/hammerspoon — macOS desktop automation scripted in Lua (hotkeys, window management, app events) (15,740★, 2026-07-08, MIT)
- skhd — https://github.com/asmvik/skhd — Simple hotkey daemon for macOS (8,041★, 2025-12-09, MIT)
- Keyboard Maestro — https://www.keyboardmaestro.com/ — Commercial macOS macro platform (hotkeys, palettes, app-scoped macros) (stars n/a, push n/a, commercial)

### Secrets management for agent workflows
John uses: 1Password `op` CLI — https://developer.1password.com/docs/cli/ (commercial, subscription)
- Bitwarden CLI (bw) — https://github.com/bitwarden/clients — CLI for the Bitwarden password manager (open clients, optional self-host via vaultwarden) (13,299★, 2026-07-17, NOASSERTION (GPL/Bitwarden License mix))
- Infisical — https://github.com/Infisical/infisical — Open-source platform for secrets, certificates, and privileged access; CLI injects env vars (28,114★, 2026-07-17, NOASSERTION (MIT + enterprise dirs))
- Doppler CLI — https://github.com/DopplerHQ/cli — Official CLI for Doppler secrets/config: `doppler run -- cmd` injects secrets as env vars (384★, 2026-07-13, Apache-2.0)
- sops — https://github.com/getsops/sops — Encrypt secrets inside files in your repo (age/KMS/PGP), decrypt on use (22,519★, 2026-07-13, MPL-2.0)
- pass + age — https://www.passwordstore.org/ and https://github.com/FiloSottile/age — The UNIX password store (GPG) and the modern simple file-encryption tool (22,888★, 2026-03-20, GPL-2.0 (pass) / BSD-3-Clause (age))

### Agent skills: authoring & distribution
John uses: skills CLI (skills.sh) + ~/.agents/skills — https://github.com/vercel-labs/skills (26,358 stars, pushed 2026-07-16)
- anthropics/skills — https://github.com/anthropics/skills — Anthropic's public repository of Agent Skills (161,840★, 2026-07-17, none listed)
- superpowers — https://github.com/obra/superpowers — An agentic skills framework and software-development methodology (256,147★, 2026-07-17, MIT)
- Claude Code plugins/marketplaces (built-in) — https://docs.claude.com/en/docs/claude-code — Native plugin + marketplace system bundling skills, commands, hooks, MCP servers (stars n/a, push n/a, product)
- MCP servers — https://github.com/modelcontextprotocol — Model Context Protocol: distribute agent capabilities as tool servers rather than markdown skills (stars n/a, push n/a, open spec (MIT))

### Just-in-time app state capture (markers)
John uses: agent-markers (09-markers demo) — workshop repo 09-markers/demo/agent-markers.js; published pattern at https://mindful-mango-accy.here.now/
- rrweb — https://github.com/rrweb-io/rrweb — Record and replay the web: DOM-level session recording library (19,882★, 2026-07-16, MIT)
- OpenReplay — https://github.com/openreplay/openreplay — Self-hostable session replay + product analytics for reproducing issues (12,234★, 2026-07-16, NOASSERTION (ELv2/MIT mix))
- Highlight — https://github.com/highlight/highlight — OSS full-stack monitoring: session replay, errors, logs, traces (9,331★, 2026-04-16, NOASSERTION (Apache-2.0 core))
- Sentry Session Replay — https://github.com/getsentry/sentry — Session replay wired to error tracking in Sentry (44,308★, 2026-07-17, NOASSERTION (FSL))
- Jam — https://jam.dev/ — Chrome extension: one-click bug reports with replay, console logs, network requests, device details (stars n/a, push n/a, commercial (free tier))

### Image generation for design variations
John uses: Codex $imagegen skill + agy (Google Antigravity CLI) — Codex: https://github.com/openai/codex; Antigravity CLI: https://github.com/google-antigravity/antigravity-cli (1,615 stars, pushed 2026-07-16)
- Gemini CLI — https://github.com/google-gemini/gemini-cli — Google's terminal agent; image generation via Gemini/Imagen models on the free tier (106,024★, 2026-07-16, Apache-2.0)
- ComfyUI — https://github.com/Comfy-Org/ComfyUI — Node-graph GUI/API/backend for diffusion models, fully local (121,079★, 2026-07-17, GPL-3.0)
- mflux — https://github.com/filipstrand/mflux — MLX-native FLUX and other image models on Apple Silicon (2,211★, 2026-06-30, MIT)
- InvokeAI — https://github.com/invoke-ai/InvokeAI — Professional creative engine/WebUI for Stable Diffusion family models (27,623★, 2026-07-15, Apache-2.0)
- AUTOMATIC1111 stable-diffusion-webui — https://github.com/AUTOMATIC1111/stable-diffusion-webui — The historically dominant SD web UI (164,189★, 2026-03-02, AGPL-3.0)

## Unverifiable / flagged
- cs — no public repo found; treated as personal/unreleased, with the honest substitutes listed in §10.
- packx — verified as John's npm package via web search (`npm install -g packx`), but it has no public GitHub repo we could find; star/license evidence unavailable.
- Oracle's exact consult architecture — the fork repo exists (johnlindquist/oracle (https://github.com/johnlindquist/oracle)) but is empty of description/stars; capabilities described here come from the workshop's own docs.
- Grok Build star data — proprietary, no public repo; existence verified via x.ai announcement coverage.
- License nuances behind every "NOASSERTION" — read the repo's LICENSE before commercial adoption (notably Crush, OpenHands, herdr, Sentry, OpenReplay, Infisical, Bitwarden).

## Also mentioned (no table needed)
- pi-session-id (https://github.com/johnlindquist/pi-session-id) — the section 01 pi extension (MIT). The *pattern* (per-command shell prefix + session-scoped overrides) ports to any agent with shell hooks.
- Zed / Finder / GitHub open-cwd targets (section 06) — editor-of-choice slots; any `open`/`code`-style CLI works.
- Linear CLI (sections 01/05) — an example policy-wrapped command; substitute your tracker's CLI.
- Tailscale (section 08) — how the Mac mini oracle server is reached; any WireGuard-style mesh works.
- wrangler / inspiration-board (section 07) — covered under Publishing above.

Human-facing page: https://dewy-sleet-n5zs.here.now/ — tables with the same data plus "pick this if…" fit guidance per category.