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

Stack Overflow Blog
Stack Overflow Blog
WordPress大学
WordPress大学
罗磊的独立博客
S
Secure Thoughts
Schneier on Security
Schneier on Security
博客园 - Franky
www.infosecurity-magazine.com
www.infosecurity-magazine.com
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
爱范儿
爱范儿
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Hacker News: Ask HN
Hacker News: Ask HN
PCI Perspectives
PCI Perspectives
Google DeepMind News
Google DeepMind News
S
Security Affairs
SecWiki News
SecWiki News
博客园 - 聂微东
Security Archives - TechRepublic
Security Archives - TechRepublic
Google Online Security Blog
Google Online Security Blog
H
Heimdal Security Blog
S
Security @ Cisco Blogs
Engineering at Meta
Engineering at Meta
C
CXSECURITY Database RSS Feed - CXSecurity.com
Cloudbric
Cloudbric
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
V
Visual Studio Blog
P
Proofpoint News Feed
Project Zero
Project Zero
T
Threat Research - Cisco Blogs
Webroot Blog
Webroot Blog
Blog — PlanetScale
Blog — PlanetScale
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
W
WeLiveSecurity
Last Week in AI
Last Week in AI
月光博客
月光博客
Microsoft Azure Blog
Microsoft Azure Blog
M
MIT News - Artificial intelligence
有赞技术团队
有赞技术团队
S
Securelist
GbyAI
GbyAI
Application and Cybersecurity Blog
Application and Cybersecurity Blog
C
CERT Recently Published Vulnerability Notes
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Cyberwarzone
Cyberwarzone
B
Blog RSS Feed
P
Palo Alto Networks Blog
H
Hacker News: Front Page
D
Docker
雷峰网
雷峰网
Latest news
Latest news
Microsoft Security Blog
Microsoft Security Blog

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - AronDaron/dataset-generator: No-code desktop app for generating high-quality synthetic datasets to fine-tune LLMs — plan-then-execute pipeline, LLM-as-judge, HuggingFace upload. GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace GitHub - Nyquest-ai/nyquest-rust-fullstack-pub: Nyquest — Semantic Compression Proxy for LLMs. 350+ rules, local LLM stage, 15-75% token savings. Full Rust stack. GitHub - TheoV823/mneme: Enforce architectural decisions in AI-assisted development. GitHub - klemenvod/TokenBrawl: A 1v1 Bomberman-style game where two LLM agents play autonomously against each other. No human plays — you watch the AIs fight. Each agent receives a text description of the board state, reasons about it, and outputs a move as JSON. The game engine executes it. Introducing the Common AI Provider: LLM and AI Agent Support for Apache Airflow Power Circuit AI: Designing Power Electronic Circuits for Motor Drives with Generative Artificial Intelligence Ask HN: How to program with IDE and LLM on CPU locally? Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis Bonsai 1-bit WebGPU - a Hugging Face Space by webml-community The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows Ask HN: Simple tooling for local LLM code critique without IDE integration? Can a General LLM Diagnose a DICOM Slice? A 10-Case Public Benchmark Charts-of-Thought: Enhancing LLM Visualization Literacy (PDF, 2026) GitHub - Mesh-LLM/mesh-llm: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. GitHub - seamus-brady/springdrift: A persistent runtime for long-lived LLM agents Writing an LLM from scratch, part 32k -- Interventions: training a better model locally with gradient accumulation Ask HN: Which LLM model and agentic CLI are you using for local development? GitHub - wayneColt/modelcascade: Route local. Escalate smart. Never overspend. Open-source multi-model cascade routing for autonomous agents. LLM pricing is 100x harder than you think GitHub - asakin/llm-primer: Pre-warmed Claude Code sessions in tmux. No startup wait. GitHub - EggerMarc/chat-rs: A multi-provider LLM framework for Rust. GitHub - SynapseKit/SynapseKit: Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS. A Claude Skill that Makes LLM Paragraphs More Bearable Does Gas Town 'steal' usage from users' LLM credits & paid services to improve itself? What's Claude Code Actually Doing? Open the Black Box with the Arthur Engine Milla Jovovich's New Open Source LLM Memory App and the Dark Code Problem Your intuition of LLM token usage might be wrong Show HN: Bloomberg Terminal for LLM ops – free and open source GitHub - 0xchamin/mcptube: Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more. Show HN: Open KB: Open LLM Knowledge Base Your LLM is a compiler, not a runtime GitHub - sapountzis/Unslop: A Web Feed That Deserves You crates.io: Rust Package Registry Beyond Karpathy's LLM-Wiki: The Necessity of Cognitive Governance GitHub - amitshekhariitbhu/llm-internals: Learn LLM internals step by step - from tokenization to attention to inference optimization. GitHub - parallem-ai/parallem: An expressive library for running agents with the Batch API. GitHub - stfurkan/pi-llm LLM-Wiki Show HN: Formal – Formal verification for AI-generated code using Lean 4 LRTS – Regression testing for LLM prompts (open source, local-first) LLM Wiki Skill: Build a Second Brain with Claude Code and Obsidian I built an LLM Wiki and RAG solution: here's a demo for a security KB The biggest advance in AI since the LLM Predict-Rlm: The LLM Runtime That Lets Models Write Their Own Control Flow the-synthetic-library/the-synthetic-mind at main · joshferrer1/the-synthetic-library GitHub - yisding/reviewwiggum GitHub - Donnyb369/mcp-spine: Context Minifier & State Guard — Local-first MCP middleware proxy GitHub - Beledarian/wgpu-llm: A from-scratch LLM inference engine that uses wgpu (the cross-platform WebGPU implementation) to dispatch WGSL compute shaders for every math operation a Transformer needs. No CUDA. No Python. No massive framework dependencies. Just Rust, raw shaders, and your GPU. GitHub - anitiue/Hindsight: An experience-driven self-improvement framework for LLM agents — 基于经验的 LLM Agent 自我改进框架 GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. GitHub - alainnothere/AmdPerformanceTesting: Amd Performance Testing Ask HN: Is a purely Markdown-based CRM a terrible idea? Optimized for LLM agents Context Engineering - LLM Memory and Retrieval for AI Agents | Weaviate little_helper_tui/letter.md at main · sleepyeldrazi/little_helper_tui GitHub - EvanZhouDev/umr: The Unified Model Registry for all your local AI apps. GitHub - JordanCT/VigIA-Orchestrator Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain A Taxonomy of RL Environments for LLM Agents Llama LLM Network Feture GitHub - genedeng-ca/ai-mac-migration: AI-powered Mac-to-Mac migration tool - replace Apple Migration Assistant with intelligent, selective transfer using local LLMs GitHub - lunargate-ai/gateway: High-performance self-hosted AI gateway (OpenAI-compatible) with routing, retries, and streaming GitHub - AuthBits/webmcp: A lightweight, prompt-driven MCP web research server for high-quality LLM powered information extraction. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
GitHub - Esubaalew/appctl: Give an LLM safe, auditable tools for your existing app.
esubaalew · 2026-05-07 · via Hacker News - Newest: "LLM"

Give an LLM safe, auditable tools for your existing app.

appctl is a command-line operator layer for real applications. Point it at an HTTP API, OpenAPI document, database, Supabase/PostgREST service, MCP server, or supported framework project. It writes a local .appctl/ contract, exposes the discovered actions as typed tools, and runs the tool calls requested by your configured LLM.

In practice, appctl lets you ask things like "list overdue invoices", "create a refund", or "summarize failed jobs" against your own backend without building a custom agent integration first. Your app remains the source of truth; appctl adds setup, auth handling, safety checks, execution, and local audit history.

Documentation: https://esubalew.dev/appctl
Repository: https://github.com/Esubaalew/appctl

What appctl does

  1. Reads your app surface from a supported source such as OpenAPI, Django/DRF, Rails, Laravel, ASP.NET, Strapi, Supabase/PostgREST, SQL schema, URL login flow, MCP, or a plugin.
  2. Generates .appctl/schema.json and .appctl/tools.json, a local contract describing what the model is allowed to call.
  3. Sends your prompt to the configured provider and executes requested tool calls through appctl.
  4. Records tool calls, arguments, provenance, status, and results in local history so the run can be inspected later.

appctl is not a web framework, hosted database, or LLM provider. It sits beside your existing application and controls how an AI agent can use it.

Install

cargo install appctl

Build from a clone, or install with a custom web UI bundle: see Installation.

Commands (overview)

Command Purpose
appctl setup Guided first-run flow: provider, sync source, checks, and next steps.
appctl init Create .appctl/config.toml and store provider secrets.
appctl sync Generate .appctl/schema.json and tools.json from a source (e.g. --openapi, --django, --db).
appctl chat / appctl run Send a prompt; the model may call tools via appctl.
appctl serve HTTP and WebSocket API plus bundled web UI.

Quick start

appctl setup
appctl chat

Run setup from the app/project folder you want to control. It creates or reuses that folder's .appctl/, guides provider setup, syncs tools, verifies the target API, and tells you exactly how to open the terminal or web console.

For protected APIs, prefer environment-backed target auth:

export API_TOKEN="..."
appctl setup
# Auth header prompt:
# Authorization: Bearer env:API_TOKEN

Advanced manual setup is still available:

appctl init
appctl sync --openapi https://api.example.com/openapi.json --base-url https://api.example.com
appctl doctor --write

Full CLI reference, sync sources, providers, serve, and plugins are covered in the documentation.

Demos

The examples below use an OpenAPI-backed app and Ollama. Your session shows the synced .appctl/ contract, discovered tools, and inline tool calls (arguments and JSON responses). Slash commands adjust provider, model, read-only mode, and dry-run.

Terminal session: hello and list projects

appctl chat: greeting and list_projects with empty result

$ ./target/release/appctl chat

┌ appctl chat [ollama] ─────────────────────────┐
│ Synced application session                      │
│ app dir: .appctl                                │
└─────────────────────────────────────────────────┘

┌ commands ───────────────────────────────────────┐
│ resources: 2  tools: 7                          │
│ /provider NAME  /model NAME  /read-only on|off   │
│ /dry-run on|off  /exit                           │
└─────────────────────────────────────────────────┘

appctl[ollama]▶ hi
> hi
I am appctl, your application operations agent.

appctl[ollama]▶ list projects
> list projects
● list_projects_api_v1_projects_get  id call_mrynczr6
{
  "limit": 10,
  "offset": 0
}
→ ok  15ms  id=call_mrynczr6
{
  "data": [],
  "status": 200
}
There are currently no projects. Let me know if you'd like to create one.

Terminal session: create a project (confirm before write)

Natural language create project with confirmation and HTTP 201

appctl[ollama]▶ ow create one pls
Sure! To create a project, I'll need a name and a short description.
Should the project be active right away (yes/no)?

appctl[ollama]▶ appctle is its name and it is CLI app that works for devs
  and clients for free and it should be active

? Execute 'create_project_api_v1_projects_post' with payload
  { "active": true, "description": "...", "name": "appctle" }

}? yes

● create_project_api_v1_projects_post  id call_f26550z0
{
  "active": true,
  "description": "CLI app that works for devs and clients for free",
  "name": "appctle"
}
→ ok · 65ms · id=call_f26550z0
{
  "data": {
    "active": true,
    "created_at": "2024-04-23T12:43:34.391067",
    "description": "CLI app that works for devs and clients for free",
    "id": 1,
    "name": "appctle"
  },
  "status": 201
}

Project created successfully:
- ID: 1
- Name: appctle
- Description: CLI app that works for devs and clients for free
- Active: Yes

Terminal session: list projects as a table

list_projects after create, with formatted table

appctl[ollama]▶ List the projects now
● list_projects_api_v1_projects_get  id call_1dxqpvkz
{
  "limit": 10,
  "offset": 0
}
→ ok · 2ms · id=call_1dxqpvkz
{
  "data": [
    {
      "active": true,
      "created_at": "...",
      "description": "CLI app that works for devs and clients for free",
      "id": 1,
      "name": "appctle"
    }
  ],
  "status": 200
}

Here's the current project list:
┌────┬─────────┬─────────────────────────────────────────────┬────────┐
│ ID │ Name    │ Description                                 │ Active │
├────┼─────────┼─────────────────────────────────────────────┼────────┤
│ 1  │ appctle │ CLI app that works for devs and clients...  │ Yes    │
└────┴─────────┴─────────────────────────────────────────────┴────────┘

Web UI: same API, conversational formatting

With appctl serve, you can use the bundled console against the same tools. The model can follow formatting instructions (here, listing project labels with emojis, then replying with emojis only when asked).

Web chat with API status bar and emoji-heavy replies

License

MIT © Esubalew