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

P
Privacy International News Feed
I
Intezer
T
Tenable Blog
S
Schneier on Security
Project Zero
Project Zero
G
GRAHAM CLULEY
酷 壳 – CoolShell
酷 壳 – CoolShell
小众软件
小众软件
Know Your Adversary
Know Your Adversary
博客园 - 司徒正美
The Cloudflare Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
N
News and Events Feed by Topic
博客园 - 叶小钗
宝玉的分享
宝玉的分享
L
LINUX DO - 热门话题
aimingoo的专栏
aimingoo的专栏
S
Secure Thoughts
Forbes - Security
Forbes - Security
T
The Exploit Database - CXSecurity.com
D
Darknet – Hacking Tools, Hacker News & Cyber Security
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 【当耐特】
罗磊的独立博客
IT之家
IT之家
H
Hacker News: Front Page
I
InfoQ
云风的 BLOG
云风的 BLOG
S
Security Affairs
M
MIT News - Artificial intelligence
GbyAI
GbyAI
Jina AI
Jina AI
Help Net Security
Help Net Security
Engineering at Meta
Engineering at Meta
大猫的无限游戏
大猫的无限游戏
Webroot Blog
Webroot Blog
L
Lohrmann on Cybersecurity
A
About on SuperTechFans
Attack and Defense Labs
Attack and Defense Labs
The Register - Security
The Register - Security
V
V2EX
G
Google Developers Blog
D
DataBreaches.Net
Apple Machine Learning Research
Apple Machine Learning Research
C
Cybersecurity and Infrastructure Security Agency CISA
J
Java Code Geeks
W
WeLiveSecurity
Cloudbric
Cloudbric
T
Tor Project blog

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
Autonomy — 自律型 AI 代理人系統 | Bill Liu
Bill Liu · 2026-06-20 · via Show HN

AgentLoop · ConversationLoop Python 3.13 · 自律執行中

Beam Search 候選排序受管行動閘道程序技能學習為核心,
打造真正能自主感知、規劃、執行並持續進化的 AI 代理人系統。

探索核心模組 查看原始碼

0 內建 Procedure Skills

0 + 內建工具

0 支援 AI Provider

0 Beam Width

AgentLoop 是 Autonomy 的核心驅動器——一個「自導向任務迴圈」,不需要人工介入即可從目標出發,自主選擇工具、執行行動並從結果中學習。

每個 Turn 的執行流程:①從技能庫選取相關 ProcedureSkill,②由 LLM 提案 + RecipeEngine 產出候選動作路徑,③以 5 維評分排序(Beam Width=3),④透過 ActionGateway 受管執行,⑤評估結果並觸發學習。

終止條件明確:ACHIEVED(目標完成)、BLOCKED(無法繼續)、NO_CANDIDATESAPPROVAL_DENIEDMAX_STEPS_REACHED、或 FAILED——系統永遠不會陷入無限循環。

AgentLoop ActionGateway CandidateSelector LearningLoop CuratorDaemon

📚

disclose_procedure_skills() 選取相關技能

💡

generate_candidates() LLM 提案 + Recipe Engine

📊

rank_candidates() 5 維評分 · Beam Width=3

ActionGateway.execute_next() ApprovalPolicy 授權 · 受管執行

🧠

evaluate_outcome() + learn() 結果評估 · Recipe 學習

自導向代理人迴圈

AgentLoop.run(goal, max_steps=12) 啟動後完全自主執行,每步驟透過 run_turn() 推進。支援互動模式(interactive=True)與批次模式,所有事件均以 run_id 記錄於 AutonomyStore

受管行動閘道

所有工具呼叫必須通過 ActionGatewayApprovalPolicy 授權。每個動作帶有 RiskLevel(LOW / MEDIUM / HIGH)、expected_effectverification_plan,確保執行可控、可審計。

5 維 Beam Search 評分

CandidateSelector 以 evidence_strength(+0.30)、purpose(+0.10)、risk(−0.35)、side_effects(−0.20)、penalty(−1.0)五個維度計算總分,選出前 beam_width=3 名候選路徑送往執行。

混合結果評估

DeterministicOutcomeEvaluator 優先判斷執行失敗(直接 BLOCKED),成功但結果不確定時再交由 ModelAssistedOutcomeEvaluator 呼叫 LLM 語義判斷——最小化昂貴的模型呼叫次數。

程序技能庫(13 內建)

ProcedureSkillLibrary 內建 13 個 bundled skills,涵蓋 api-debugging、browser-navigation、code-editing、codebase-documentation、plan、procedure-skill-authoring、process-management、requesting-code-review、systematic-debugging、technical-spike、TDD、website-inspection、writing-plans,每步動態選取最相關技能載入。

後執行學習迴路

每次 Run 結束後,LearningLoop.review_run() 自動觸發:若結果為 ACHIEVED 且有 ≥2 個成功步驟,自動起草新 ProcedureSkillDraft(信心度 0.85),生成 LearningProposal 等待審核。

Action Recipe 引擎

RecipeEngine 監控每個成功動作的 SHA-256 指紋——當同一動作成功次數 ≥ candidate_threshold=2,自動升格為候選 Recipe,下次直接作為行動選項(source=action_skill)提出,無需 LLM 重新推理。

技能策展守護程序

每次 Run 結束後,CuratorDaemon 在後台執行緒(daemon=True)非同步啟動 SkillCurator.apply_auto_merges(),自動偵測並合併重複(信心 0.95)或子集(信心 0.90)技能,防止技能庫膨脹。

可擴展工具集目錄

TOOLSET_CATALOG 涵蓋 4 個預設啟用工具集:file、terminal、search、skills,加上 opt-in 的 project(git / JSON / YAML / 測試探索)與 browser(Playwright headless Chromium,11 工具)。規劃中:memory、delegate、cronjob、computer_use。

完整事件溯源稽核

AutonomyStore 以 Event Sourcing 模式記錄整個執行生命週期:run_started → skills_selected → candidates_ranked → action_selected → approval_decision → observation → outcome_evaluated → recipe_learned → learning_review → run_finished,完整可重播。

TUI 終端互動介面

autonomy tui 啟動豐富終端介面,提供 session 總覽面板、回合記錄、Action trail、compact/full 切換模式與 / 指令面板。自然語言直接流入 AgentLoop,UI 永遠不直接執行工具。

多 Provider 支援

支援 ollama(本地)與 8 個 OpenAI-compatible providers:openai-api、nvidia、openrouter、deepseek、xai、zai、kimi-coding、alibaba。提供 API 金鑰管理與 provider 設定,autonomy doctor 可檢查端點走通性。

score =

evidence_strength × +0.30 purpose × +0.10 risk × −0.35 side_effects × −0.20 penalty × −1.0

Entry · Interactive TUI / CLI run

SessionShell → ConversationLoop autonomy tui · 互動式對話

AgentLoop.run(goal) autonomy run · max_steps · UUID run_id

Turn Loop · run_turn()

ProcedureSkillLibrary index() · load_selected()

RecipeEngine candidates_for() · learn()

CandidateSelector beam_width=3 · 5-dim score

Execution · ActionGateway

ApprovalPolicy authorize(action, interactive)

ActionGateway execute_next() · risk assessment

ToolRegistry execute(action) → Observation

Post-Run · finish_run()

OutcomeEvaluator Deterministic + Model-assisted

LearningLoop review_run() · draft skill

CuratorDaemon async thread · auto-merge

Persistence · AutonomyStore

📁 runs

📡 events

⚗️ recipes

📚 skills

💡 proposals

🗂️ curator_log

TOOLSET_CATALOG — 工具集 & AI Providers

fileread / write / patch / diff / outline / symbol_search / syntax_check…

terminalshell.execute / process.start / poll / log / wait / stop

projectgit.status/diff/log · json.parse · yaml.parse · python.test_discover (opt-in)

browserPlaywright Chromium · navigate / snapshot / click / screenshot… (opt-in)

memoryPersistent Workspace Memory & Context Injection

delegate / cronjob / computer_useplanned

支援 AI Provider

Ollama本地部署 · http://127.0.0.1:11434/v1

OpenAI APIopenai-compatible · OPENAI_API_KEY

NVIDIAintegrate.api.nvidia.com · kimi-k2.6

OpenRouterOPENROUTER_API_KEY

xAI · Kimi · Alibaba · ZAIXAI_API_KEY · KIMI_API_KEY · DASHSCOPE_API_KEY…

api-debugging

browser-navigation

code-editing

codebase-documentation

plan

process-management

requesting-code-review

systematic-debugging

technical-spike

test-driven-development

website-inspection

writing-plans

每次執行 Turn 時,model.select_procedure_skills() 依可用工具名稱動態篩選並載入最相關技能;執行成功且達到門檻後,LearningLoop 將自動起草新技能並生成 LearningProposal(CANDIDATE 狀態)。

Bill Liu

Bill Liu

Autonomy 框架設計者 & AI Agent 系統工程師

設計並實作了 Autonomy 自律型 AI 代理人框架,核心貢獻包括:Beam Search 候選評分系統、受管行動閘道(ActionGateway)、後執行學習迴路(LearningLoop)、以及後台技能策展守護程序(CuratorDaemon)。

致力於讓 AI 代理人在真實工程環境中可靠運行——從程式碼編輯、瀏覽器自動化到系統除錯,透過可組合的技能庫與事件溯源架構實現完整可審計性。

LinkedIn GitHub

準備好打造你的自律型 AI 代理人了嗎?

Fork Autonomy,添加你的工具集、訓練專屬技能庫,讓代理人在你的領域自主作業。

前往 GitHub 聯絡作者