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

G
Google Developers Blog
Spread Privacy
Spread Privacy
V
Visual Studio Blog
爱范儿
爱范儿
Apple Machine Learning Research
Apple Machine Learning Research
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
GbyAI
GbyAI
Google DeepMind News
Google DeepMind News
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
V2EX
J
Java Code Geeks
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Blog — PlanetScale
Blog — PlanetScale
N
Netflix TechBlog - Medium
B
Blog RSS Feed
博客园 - 【当耐特】
有赞技术团队
有赞技术团队
The Register - Security
The Register - Security
Latest news
Latest news
The Cloudflare Blog
Project Zero
Project Zero
月光博客
月光博客
U
Unit 42
Vercel News
Vercel News
Attack and Defense Labs
Attack and Defense Labs
Know Your Adversary
Know Your Adversary
V
Vulnerabilities – Threatpost
F
Full Disclosure
Schneier on Security
Schneier on Security
Google Online Security Blog
Google Online Security Blog
MyScale Blog
MyScale Blog
L
Lohrmann on Cybersecurity
C
CERT Recently Published Vulnerability Notes
博客园 - 叶小钗
腾讯CDC
博客园 - 三生石上(FineUI控件)
T
The Blog of Author Tim Ferriss
D
Darknet – Hacking Tools, Hacker News & Cyber Security
博客园 - Franky
S
Security Affairs
Hacker News: Ask HN
Hacker News: Ask HN
Security Latest
Security Latest
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
MongoDB | Blog
MongoDB | Blog
D
DataBreaches.Net
SecWiki News
SecWiki News
Recorded Future
Recorded Future
NISL@THU
NISL@THU
Hacker News - Newest:
Hacker News - Newest: "LLM"
Cloudbric
Cloudbric

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 - sorena-ai/service-catalog-mcp: Service Catalog MCP -- Managing microservices by understanding the codebase
redbrandi · 2026-06-23 · via Show HN

AI-powered platform for making batch code changes across multiple GitHub repositories. Connect any MCP client, describe a change in plain English, and Service Catalog finds the right repos, generates diffs via Claude or Devin, pushes branches, and opens pull requests.

Connect

Hosted service

claude mcp add --transport http service-catalog-mcp https://mcp.infraas.ai

Or add manually to your MCP client config:

{
  "mcpServers": {
    "service-catalog": {
      "url": "https://mcp.infraas.ai"
    }
  }
}

Self-hosted

claude mcp add --transport http service-catalog-mcp http://localhost:8200

See Self-hosting below to start the server locally.

Self-hosting

Prerequisites

  • Docker and Docker Compose
  • A GitHub personal access token with repo scope
  • An Anthropic API key or a Devin account

1. Configure

cp .env.example .env
# Edit .env — at minimum set GITHUB_TOKEN and ANTHROPIC_API_KEY

2. Set up your CLI provider

Service Catalog generates code changes by running a CLI agent inside each cloned repository. Two providers are supported.

Claude (default)

Set in .env:

CLI_PROVIDER=claude
ANTHROPIC_API_KEY=sk-ant-...

That's all — no other setup needed.

Devin

Devin authenticates via a credentials file on your host machine. Set it up once, then mount the file into the container so it persists across restarts.

Step 1 — authenticate on your host:

# Install the Devin CLI if you haven't already
curl -fsSL https://cli.devin.ai/install.sh | bash

# Log in — this saves credentials to ~/.local/share/devin/credentials.toml
devin auth login --force-manual-token-flow

Step 2 — mount the credentials file. Add this volume to the mcp-server service in docker-compose.yml:

volumes:
  - ~/.local/share/devin/credentials.toml:/root/.local/share/devin/credentials.toml:ro
  - batch-workspaces:/var/batch-workspaces
  - repo-clones:/repos

Step 3 — set in .env:

3. Start

The MCP server is available at http://localhost:8200.

4. Connect your MCP client

claude mcp add --transport http service-catalog-mcp http://localhost:8200

How it works

A batch change follows four steps, each confirmed before moving to the next:

  1. Find repossearch_repos finds repos by language, framework, dependency, or a plain-English query.
  2. Planpropose_plan calls the planner LLM and proposes a per-repo task; adjust with replan or set_repo_subtask before approving.
  3. Diffstart_diffs runs the CLI agent in each repo; wait_for_diffs polls progress; review diffs with chat_repo.
  4. Push & PRpush_repos pushes branches; get_workflow_runs shows CI; create_pr opens pull requests.

Tools

Discovery

Tool Description
search_repos Search by dependency, language, framework, platform, GitHub Action, or NL query
get_codebase_glossary Project-specific terminology and search hints
list_repository_groups List saved repository groups
get_repository_group Fetch a saved group by name
list_user_repositories All linked repositories with indexing status
index_repository Manually trigger indexing for a specific repo

Batch change

Tool Description
propose_plan Start a batch — runs the planner and proposes per-repo tasks
replan Re-run the planner with a hint
set_repo_subtask Edit one repo's task description or base branch
add_repos Add repos mid-batch
remove_repos Remove repos from the current batch
start_diffs Kick off the CLI agent for all pending repos
wait_for_diffs Poll diff progress; streams updates, returns after ~25 s
chat_repo Ask questions (mode="qa") or request edits (mode="edit") on a repo's diff
inspect_batch View session status, PR status, or a specific file's diff
push_repos Push branches for ready repos
create_pr_prep Draft PR title and body for each repo
set_pr_prep Edit a repo's PR title or body
create_pr Open pull requests
update_pr Edit an open PR
close_pr Close PRs without merging
cancel_batch Cancel all in-flight tasks and wipe the session

CI/CD

Tool Description
get_workflow_runs GitHub Actions status across repos — call without args after push_repos to check all pushed repos
get_workflow_jobs Per-job/step detail for a run; use failed_only=True for triage

Environment variables

Variable Default Description
LOCAL true true = single-user local mode; false = cloud mode (requires Auth0 + MongoDB)
GITHUB_TOKEN Personal access token with repo scope (local mode)
CLI_PROVIDER claude Code-change agent: claude or devin
ANTHROPIC_API_KEY Required when CLI_PROVIDER=claude
CLAUDE_CLI_DEFAULT_MODEL Override the model used by the Claude CLI
DEVIN_MODEL Override the model used by the Devin CLI
MONGODB_URI MongoDB connection string (falls back to TinyDB if unset)
MONGODB_DATABASE service-catalog MongoDB database name
REDIS_URL Redis URL (falls back to in-memory cache if unset)
MCP_PORT 8200 Port the MCP server listens on
LOG_LEVEL INFO Log verbosity
LANGSMITH_API_KEY Enable LangSmith tracing (optional)
CLONE_REPO_BASE_DIR /repos Base directory for indexer clones
BATCH_CLONE_BASE_DIR /var/batch-workspaces Base directory for batch change workspaces

Cloud-mode variables (LOCAL=false): MCP_AUTH0_DOMAIN, MCP_AUTH0_CLIENT_ID, MCP_AUTH0_CLIENT_SECRET, MCP_AUTH0_AUDIENCE, MCP_BASE_URL, GITHUB_APP_ID, GITHUB_APP_NAME, GITHUB_PRIVATE_KEY_PATH.

License

MIT — see LICENSE.