惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
Threat Research - Cisco Blogs
H
Hacker News: Front Page
IT之家
IT之家
I
Intezer
GbyAI
GbyAI
MongoDB | Blog
MongoDB | Blog
博客园_首页
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
S
SegmentFault 最新的问题
D
Darknet – Hacking Tools, Hacker News & Cyber Security
T
Threatpost
Cisco Talos Blog
Cisco Talos Blog
C
Check Point Blog
P
Proofpoint News Feed
P
Privacy International News Feed
有赞技术团队
有赞技术团队
T
Tailwind CSS Blog
Scott Helme
Scott Helme
U
Unit 42
J
Java Code Geeks
W
WeLiveSecurity
H
Hackread – Cybersecurity News, Data Breaches, AI and More
C
CERT Recently Published Vulnerability Notes
小众软件
小众软件
The Hacker News
The Hacker News
L
LINUX DO - 热门话题
博客园 - 【当耐特】
G
Google Developers Blog
Latest news
Latest news
AWS News Blog
AWS News Blog
NISL@THU
NISL@THU
S
Secure Thoughts
P
Proofpoint News Feed
L
Lohrmann on Cybersecurity
F
Full Disclosure
S
Securelist
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Engineering at Meta
Engineering at Meta
Security Archives - TechRepublic
Security Archives - TechRepublic
人人都是产品经理
人人都是产品经理
T
Tor Project blog
Recent Announcements
Recent Announcements
Security Latest
Security Latest
N
News | PayPal Newsroom
A
About on SuperTechFans
Hugging Face - Blog
Hugging Face - Blog
Y
Y Combinator Blog
大猫的无限游戏
大猫的无限游戏
博客园 - Franky
T
The Blog of Author Tim Ferriss

Show HN

GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - matisiekpl/neond: DX-focused control plane for Postgres dedicated to non-critical workloads. Your postgres:latest replacement 🐘 GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
GitHub - naya-ai/promptctl: Git for your AI prompts — version, diff, and rollback LLM prompts from the CLI
shawnaya101 · 2026-06-25 · via Show HN

promptctl — Git for your AI prompts

CI License: MIT Go

Git for your AI prompts.

Track, version, diff, and rollback your LLM prompts — just like you version your code.

$ promptctl commit system --file prompts/system.txt -m "initial"
✓ Committed prompt "system" as v1

$ promptctl commit system --file prompts/system.txt -m "added citation rule"
✓ Committed prompt "system" as v2

$ promptctl diff system
--- system v1 (2026-06-01 09:12)
+++ system v2 (2026-06-03 14:47)

- You are a helpful assistant.
+ You are a helpful assistant. Always cite your sources.

$ promptctl rollback system 1 -m "reverting — citation hurt recall"
✓ Rolled back "system" to v1 → saved as v3

The Problem

Your prompts live in random places — hardcoded in files, buried in Notion docs, copy-pasted in Slack. When something breaks or stops working well, you have no idea:

  • What the prompt looked like last week when it was working
  • What changed between versions
  • Which version performed best
  • How to get back to a specific point

promptctl solves this. It's git for prompts.


Installation

Requires Go 1.22+.

go install github.com/naya-ai/promptctl/cmd/promptctl@latest

Or build from source:

git clone https://github.com/naya-ai/promptctl.git
cd promptctl
make build    # binary at bin/promptctl
# or: go build -o bin/promptctl ./cmd/promptctl/

Demo

promptctl terminal demo


Quick Start

# 1. Initialize in your project (creates .promptctl/store.json)
promptctl init

# 2. Save your first prompt version
echo "You are a helpful assistant." | promptctl commit system -m "initial"

# 3. Make a change and save it
echo "You are a helpful assistant. Always cite sources." | promptctl commit system -m "added citation rule" --model claude-3

# 4. See the history
promptctl log system --preview

# 5. Compare latest vs. previous
promptctl diff system

# 6. Roll back
promptctl rollback system 1 -m "reverting"

Commands

init

Initialize promptctl in the current directory. Creates .promptctl/store.json.

commit

Save a new version of a prompt.

# From stdin
echo "You are a helpful assistant." | promptctl commit system -m "initial"

# From a file (recommended for longer prompts)
promptctl commit system --file prompts/system.txt -m "from file"

# With metadata
promptctl commit classifier -m "optimized for speed" --model gpt-4o-mini --tag prod

# Interactive — type END on its own line to finish
promptctl commit system -m "manual entry"

Flags:

  • -m / --message — commit message (default: "add version N")
  • --model — tag with the model this prompt targets
  • --tag — add a label to this version
  • -f / --file — read content from a file instead of stdin

log

Show version history.

promptctl log                          # all prompts
promptctl log system                   # one prompt
promptctl log system --preview         # show content snippets
promptctl log system --tag prod        # filter by tag
promptctl log system --json            # machine-readable output

diff

Compare versions side by side with color highlighting.

promptctl diff system            # latest vs. previous
promptctl diff system 2          # v2 vs. latest
promptctl diff system 1 3        # v1 vs. v3

show

Show a prompt version.

promptctl show system            # latest version
promptctl show system 2          # specific version
promptctl show system --raw      # content only (good for piping)
promptctl show system --json     # full JSON
promptctl show system --copy     # copy to clipboard (macOS/Linux)
promptctl show system --version-at 2026-06-01   # version that was latest on that date

rollback

Restore a previous version. Creates a new version (non-destructive).

promptctl rollback system 1
promptctl rollback system 1 -m "reverting — citation hurt recall"

list

List all tracked prompts.

promptctl list
promptctl list --json       # JSON array with version counts
promptctl list --names      # one name per line (used by shell completions)

search

Search across content, commit messages, and tags.

promptctl search "helpful assistant"
promptctl search prod              # matches tag "prod"

export

Export all versions of a prompt to Markdown.

promptctl export system
promptctl export system > system-history.md

copy

Fork a prompt with its full version history under a new name.

promptctl copy system system-experimental

rename

Rename a prompt. All history moves with it.

promptctl rename system assistant

delete

Delete a prompt and all its versions.

watch

Auto-commit a file whenever it changes on disk. Great for editing prompts in your usual editor and automatically versioning every save.

promptctl watch prompts/system.txt --as system
promptctl watch prompts/system.txt --as system --model claude-3 --interval 2

Flags:

  • --as <name> — the prompt name to commit under (required)
  • --model — tag new versions with this model
  • --interval <seconds> — polling interval (default: 1)

Commit timestamps match the file's modification time, not when promptctl ran.

prune

Keep only the N most recent versions and discard the rest.

promptctl prune system --keep 10

stats

Show a store-wide overview.

Stats:
──────────────────────────────────────────────────
  Prompts:         4
  Total versions:  23
  Total content:   8432 chars
  First commit:    2026-06-01 09:12:00
  Last commit:     2026-06-24 15:30:44
  Most iterated:   system (12 versions)

completion

Print a shell completion script.

# Bash — add to ~/.bashrc
source <(promptctl completion bash)

# Zsh — add to ~/.zshrc
source <(promptctl completion zsh)

# Fish — save to completions directory
promptctl completion fish > ~/.config/fish/completions/promptctl.fish

Completions dynamically suggest prompt names for commands that take a <name> argument.


How It Works

promptctl stores everything in .promptctl/store.json — similar to how .git/ works. The store is discovered from your current directory or any parent, so commands work from any subdirectory.

your-project/
├── .promptctl/
│   └── store.json     ← all prompt versions live here
├── src/
└── ...

Add .promptctl/ to your project's .gitignore to keep prompt history local. If your team wants to share versions in git, track only the store file:

.promptctl/*
!.promptctl/store.json

Reading & Writing Programmatically

Several commands support --json or --raw for scripting:

# Read the latest version of a prompt
promptctl show system --raw

# Pipe the latest content into another tool
promptctl show system --raw | pbcopy

# List prompts as JSON
promptctl list --json

# Ingest output from a script
./generate-prompt.sh | promptctl commit system -m "generated"

Tagging & Model Tracking

# Tag a version for filtering
promptctl commit system -m "production" --tag prod --model claude-opus-4-8

# View only tagged versions
promptctl log system --tag prod

# Find all prompts referencing a tag
promptctl search prod

Why Zero Dependencies?

promptctl uses only Go's standard library — no external packages, no version conflicts, no go mod tidy surprises. One binary, no runtime.


Roadmap

  • Remote sync (S3, GitHub Gist)
  • Side-by-side terminal diff view
  • VS Code extension

Contributing

See CONTRIBUTING.md. PRs welcome — open an issue first for major changes.

git clone https://github.com/naya-ai/promptctl.git
cd promptctl
make test
make build

License

MIT © Shawnaya Williams