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

Microsoft Azure Blog
Microsoft Azure Blog
C
Cisco Blogs
WordPress大学
WordPress大学
H
Hackread – Cybersecurity News, Data Breaches, AI and More
The Cloudflare Blog
小众软件
小众软件
Recent Commits to openclaw:main
Recent Commits to openclaw:main
I
Intezer
Cyberwarzone
Cyberwarzone
T
The Blog of Author Tim Ferriss
博客园 - Franky
F
Fortinet All Blogs
C
Cyber Attacks, Cyber Crime and Cyber Security
G
Google Developers Blog
Recent Announcements
Recent Announcements
I
InfoQ
T
Threat Research - Cisco Blogs
V
V2EX
T
Tenable Blog
H
Help Net Security
Cisco Talos Blog
Cisco Talos Blog
T
Tailwind CSS Blog
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
The GitHub Blog
The GitHub Blog
P
Privacy & Cybersecurity Law Blog
A
Arctic Wolf
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
D
DataBreaches.Net
罗磊的独立博客
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
D
Docker
T
Tor Project blog
Attack and Defense Labs
Attack and Defense Labs
P
Proofpoint News Feed
H
Heimdal Security Blog
Engineering at Meta
Engineering at Meta
雷峰网
雷峰网
Martin Fowler
Martin Fowler
AWS News Blog
AWS News Blog
IT之家
IT之家
Google DeepMind News
Google DeepMind News
NISL@THU
NISL@THU
Google Online Security Blog
Google Online Security Blog
Vercel News
Vercel News
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
SecWiki News
SecWiki News
GbyAI
GbyAI
P
Proofpoint News Feed
月光博客
月光博客
Schneier on Security
Schneier on Security

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. 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 - 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 - jgennari/gorchestra: A Go-based orchestration platform for AI coding agents with real-time event streaming, session replay, and durable execution history.
cybrjoe · 2026-06-18 · via Show HN

Gorchestra

The private, permanent control room for AI coding work.

Run multiple Codex and Claude sessions, stream every event, inspect files and git state, and keep the whole story.

Go runtime React UI SQLite persistence SSE streaming Codex adapter

Agents perform work. Gorchestra conducts the performance.

Take your development wherever you are. Gorchestra gives you a private, permanent control room for AI coding work: open it on desktop or mobile, run multiple sessions across agents, queue follow-up messages, upload screenshots, switch into planning mode, inspect files and git state, and come back to the same durable history after refreshes, reconnects, and restarts.

Gorchestra live session demo

The Runtime At A Glance

Run Coordinate Inspect Remember
Launch Codex or Claude sessions from one local server. Queue work, attach images, and switch between fast and planning flows. Browse files, inspect git-aware changes, and edit text in-session. Store ordered session history in SQLite.
Tune model, reasoning, service tier, and execution mode. Keep multiple sessions moving at once from desktop or mobile. Jump from file-change diffs straight into Monaco. Reconnect with replay instead of losing context.

Why It Exists

Coding agents are useful, but serious work falls apart when everything is trapped in a single chat window. Gorchestra turns each run into an operating surface: start a session, watch what the agent is doing, inspect file and git changes, queue the next step, and keep the full history after refreshes or restarts.

It is built for getting work done locally:

  • Pick a workspace and start Codex or Claude.
  • Watch messages, thinking, tool calls, logs, errors, and file edits as they happen.
  • Queue follow-up prompts while the current run is still working.
  • Open changed files, review diffs, inspect git state, and edit Markdown or text without leaving the app.
  • Come back later and see the same ordered session history.

Gorchestra main session view with live transcript, activity rail, file explorer, and prompt composer

Quick Tour

Start a session, choose a workspace, and let the agent run. Gorchestra keeps the live transcript, workspace tools, and session controls together so you do not have to bounce between terminal tabs, editor windows, and logs.

  • Tune Codex options like model, reasoning effort, service tier, planning mode, and dangerous mode.
  • Follow messages, thinking, tool calls, command output, file edits, errors, and debug events in one transcript.
  • Keep typing while a run is active, queue messages, attach images, and answer agent-requested prompts when a run needs input.
  • Browse, search, preview, and edit workspace files from the side rail.
  • Review file-change diffs and jump straight into the editor for the changed file.
  • Refresh or reconnect without losing the session history.

Gorchestra showing multiple sessions with queued follow-up work

Install

Gorchestra is meant to run as one local binary with the React UI embedded inside it.

Homebrew

brew install jgennari/tap/gorchestra
gorchestra --open

The published tap is jgennari/homebrew-tap; the formula builds Gorchestra from the tagged source archive with Go and installs the gorchestra binary.

Run Gorchestra as a background service:

brew services start jgennari/tap/gorchestra
open http://127.0.0.1:15173
brew services stop jgennari/tap/gorchestra

The Homebrew service reads $(brew --prefix)/etc/gorchestra/gorchestra.env. Edit that file and restart the service to change the port, data directory, workspace roots, or Codex binary path.

Direct Download

Download the archive for your platform from GitHub Releases, unpack it, and run the binary.

macOS and Linux:

tar -xzf gorchestra_<version>_<os>_<arch>.tar.gz
./gorchestra --open

Windows:

Expand-Archive .\gorchestra_<version>_windows_<arch>.zip -DestinationPath .\gorchestra
.\gorchestra\gorchestra.exe --open

Release targets:

  • darwin/arm64
  • darwin/amd64
  • linux/amd64
  • linux/arm64
  • windows/amd64
  • windows/arm64

Real Codex sessions require the Codex CLI to be available on PATH, or configured with --codex-bin.

Use

Start Gorchestra and open the browser:

By default, Gorchestra binds to 127.0.0.1:8080 and stores SQLite data in the OS app data location.

Common options:

gorchestra --host 127.0.0.1 --port 8081
gorchestra --config ~/.config/gorchestra/gorchestra.env
gorchestra --data-dir ~/.gorchestra-dev
gorchestra --workspace /path/to/repo
gorchestra --workspace-root /path/to/allowed/root
gorchestra --codex-bin /path/to/codex
gorchestra --codex-model gpt-5
gorchestra --codex-sandbox workspace-write
gorchestra --codex-network-access=false
gorchestra --codex-web-search=cached
gorchestra --version

--data-dir creates the directory if needed and stores SQLite at <data-dir>/gorchestra.db. --db is still available as an exact SQLite path override and takes precedence over --data-dir.

Default data paths:

macOS: ~/Library/Application Support/Gorchestra/gorchestra.db
Linux: $XDG_DATA_HOME/gorchestra/gorchestra.db
Linux fallback: ~/.local/share/gorchestra/gorchestra.db

Environment equivalents include GORCHESTRA_HOST, GORCHESTRA_PORT, GORCHESTRA_DATA_DIR, GORCHESTRA_DB, GORCHESTRA_WORKSPACE, GORCHESTRA_OPEN, and the GORCHESTRA_CODEX_* variables matching the Codex flags.

Config files use the same env-style names:

GORCHESTRA_HOST=127.0.0.1
GORCHESTRA_PORT=15173
GORCHESTRA_DATA_DIR=/opt/homebrew/var/gorchestra
GORCHESTRA_WORKSPACE=~
GORCHESTRA_WORKSPACE_ROOTS=~
GORCHESTRA_OPEN=false
GORCHESTRA_CODEX_BIN=codex

GORCHESTRA_CONFIG is the environment equivalent of --config. GORCHESTRA_WORKSPACE_ROOTS accepts multiple paths separated by the OS path-list separator (: on macOS/Linux).

Remove local app data:

rm -rf "$HOME/Library/Application Support/Gorchestra"
rm -rf "${XDG_DATA_HOME:-$HOME/.local/share}/gorchestra"

Codex shell commands run with network access enabled by default. Codex native web search runs in live mode by default; use --codex-web-search=cached or --codex-web-search=disabled to change it.

Build From Source

Prerequisites:

  • Go 1.23 or newer
  • Bun 1.3 or newer

Build the release binary with embedded frontend assets:

This installs frontend dependencies with Bun, builds the Vite app, stages web/dist into internal/webassets/dist, runs go test ./..., builds dist/gorchestra, and writes dist/SHA256SUMS.

Run the source-built binary:

Staged assets under internal/webassets/dist are committed so go test ./... and go build ./cmd/app work from a checkout. bun run build refreshes that directory from the latest Vite output before compiling the release binary.

Tests

Backend:

Frontend:

cd web
bun run test
bun run build

Production:

bun run build
./dist/gorchestra --version

dist/SHA256SUMS contains SHA-256 checksums for local release artifacts.