标签 · Agent Infrastructure

Recent picks

13picks · chronological

09-08

OpenClaw 2.0, Accidentally

OpenClaw 2.0 is the project's largest update yet, assembled by 933 contributors—569 first-timers—across over 16,000 pull requests, and follows an uncharacteristic seven-week release gap. The release emphasizes lowering the barrier to first use: setup reuses existing ChatGPT/Claude subscriptions, API keys, or local models already on the machine, while much configuration is deferred or eliminated. The rebuilt browser app becomes a first-class surface for setup, resuming work, and live participation. From a simple inbox-to-Telegram notification flow, the post argues, a Claw can grow into cross-app tasks like answering a brother's iMessage by finding a receipt, and finally into multiplayer via shared cloud sessions that let team members join or take over a task with context intact. Written as a product announcement, it offers community stats and feature direction but no architectural or code-level technical detail.

openclaw.ai · 5 min · Agent Infrastructure · Agents · Ai Tooling

08-21

DeepSeek Harness: A Plugin-Centric Runtime for AI Agents

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI with a plugin-everything architecture powered by Cordis, a framework designed around spatiotemporal composability. It is currently in developer preview, so breaking changes are expected. You can run it from npm or from source, and it launches a local Web UI at 127.0.0.1:3080 by default. The project aims to be a modular runtime for building and operating AI agents, and is suited for engineers who want an extensible, self-hosted agent infrastructure rather than a closed product. Community support is available via GitHub Discussions and Discord, and plugins can use the 'dsh-plugin' topic for discoverability.

github.com · 2 min · Agent Harness · Agent Infrastructure · Agents

08-19

Agents need a computer, not a container: @cloudflare/computer

Cloudflare has released an early preview of @cloudflare/computer, an open-source agent runtime that pushes against the default assumption that every agent needs its own container. The package's core is a durable, SQLite-backed virtual filesystem called a workspace, which can be shared across execution backends behind one exec(string, options) interface. Two backends are included: an isolate-based backend that translates shell code into JavaScript via just-bash and runs it in a worker, and a container backend using a FUSE mount so file changes are synced back. The post includes code showing how to attach the workspace to an agent on a Durable Object with @cloudflare/think, and argues isolates are the only realistic path to scaling to billions of agents because they can spin up, tear down, and hibernate with state. Aimed at engineers building agent harnesses. The library is in early preview and ships without benchmarks.

blog.cloudflare.com · 12 min · Agent Infrastructure · Agents · AI Engineering

08-17

Harness Swap Lifts Same Model from 46.7% to 66.7% Success

In a Composio benchmark, DeepSeek V4 Flash running across 8 agent harnesses passed 20 of 30 hard tasks with Pi (66.7%), while Claude Code, Codex, and Deep Agents each passed 16. Pi's cost per successful task was $0.028, about 1/7 of Claude Code's $0.195. Community numbers show Pi and DeepSeek hitting 99.93% cache hits, processing nearly 1B input tokens for just $2.65 instead of an estimated $132. The article explains DeepSeek's prefix cache: matches must start from the first token, so harnesses must keep the prompt head stable. Reasonix and pi-deepseek-cache demonstrate concrete tactics: frozen environment summaries at startup, append-only context, separate sessions for executor and planner, and hash-cached deterministic summaries, cutting input token prices by 98-99%. Useful for engineers choosing agent harnesses or optimizing LLM API spend.

www.infoq.cn · 6 min · Agent Engineering · Agent Infrastructure · Cost Optimization

08-14

DeepSeek Harness: Everything Is a Plugin on the Cordis Kernel

DeepSeek launched DeepSeek Harness right after V4 Pro, built around the idea that everything is a plugin. The core, Cordis, only handles plugin loading, unloading, and dependency management, allowing hot-swapping during agent runs; an 88-page paper describes temporal and spatial composability. UI, tools, skills, storage, and the agent loop are all exposed as plugins, with 100+ first-party plugins and a community plugin marketplace. Setup is a single `npx @deepseek-ai/dsh web` command, and the harness is not locked to DeepSeek models—custom providers, base URLs, protocols, and model lists are supported. The post walks through four modes: Standard, PTC (packing multiple tool round-trips into one run_code), Minimal, and Create, where the agent can inspect its own Cordis environment, build a plugin, and attach it mid-run. Sessions are append-only event logs, making failure traces observable, auditable, and reproducible. It also flags steep price increases for V4 Pro (cache hits up 12x, peak output ¥27) and admits the UX is rough for non-developers. Useful for engineers interested in agent-harness design and composability.

x.com · 7 min · Agent Architecture · Agent Infrastructure · Ai Tooling

08-10

Cloudflare OS: an open source agent workspace with capability-based governance

Cloudflare has open-sourced Cloudflare OS, the agent workspace it uses internally, to bring AI leverage beyond programmers. A workspace is grounded in company-curated context and skills, and starts each agent with zero access. Resources are exposed as typed bindings, while Gatekeepers—service-specific Workers—hold credentials, enforce policy, and log every observed resource. Sharing a dashboard does not become a way to leak an underlying table, because the platform re-checks the viewer against the observation log. Apps are full-stack Workers with their own SQLite state, and the same server methods are callable by both users and agents. Model routing and spend run through AI Gateway, so admins can set budgets and pick models per task. The code is on GitHub and deployable into a Cloudflare account, with a reference deployment included. Written for engineers working on agent infrastructure, access control, and internal development platforms.

blog.cloudflare.com · 16 min · Agent Infrastructure · AI Agents · Capability Security

08-08

Cloudflare Computer: How to Cut AI Agent Sandboxing Costs by 80%

The default way to sandbox AI agents is to keep a full Linux container alive for every agent. Cloudflare Computer proposes a split: the Workspace Durable Object (with a SQLite VFS) owns authoritative project state; ordinary reads, searches and edits run in a Worker isolate via workspace.fs and just-bash; real Linux operations like npm install and build start a container on demand, and a post-command pull synchronizes changes back. Using a small Vite site as the test case, the author shows code for switching backend between worker-shell and container, and warns that exitCode 0 alone is not durability — sync.status must be 'complete'. A cost model projects that dropping container duty cycle from 100% to 10% reduces monthly cost from ~$36.83 to ~$7.53 (79.6%), while node_modules is deliberately kept disposable. A strong read for engineers building coding agents, sandboxes, or durable workspaces.

x.com · 10 min · Agent Infrastructure · Cloudflare · Cost Optimization

08-08

Virtual filesystem and pluggable runtimes for AI agents

Cloudflare Computer is a virtual filesystem built inside a Durable Object. The authoritative state lives in SQLite, and a single pluggable execution entry point, workspace.runtime.exec, dispatches work to one of three backends. The container backend projects SQLite state into a sandbox as a real FUSE mount, allowing full Linux userland binaries and network access. The isolate shell backend runs bash in a Dynamic Worker and reaches the authoritative Workspace over Workers RPC, avoiding a second store. The isolate JavaScript backend evaluates ECMAScript modules in a Dynamic Worker with structured I/O, durable relative imports, and Workspace-backed node:fs/promises. A Workspace can also be used standalone as a filesystem without a backend. The project is explicitly preview-only, not for production, but includes docs, runnable examples, and fs-bench benchmarks. Useful for engineers exploring agent infrastructure, sandboxed runtimes, and cloud-native file systems.

github.com · 5 min · Agent Infrastructure · Agents · Durable Objects

07-18

What we’ve learned building cloud agents

Cursor shares one year of lessons from building cloud agents. The biggest takeaway: a cloud agent's output quality depends almost entirely on having a full development environment. Unlike local agents that inherit your laptop's environment, cloud agents need it reconstructed from scratch. This led to building VM hibernation/resumption pipelines, checkpoint/restore/fork mechanisms, secret redaction, network policies, and credential management — essentially enterprise IT for agents. For reliability, early work-stealing architecture managed only one 9 of uptime. Migrating to Temporal's durable execution framework pushed past two 9s, handling over 50 million actions per day across 7 million+ unique workflows, with 40%+ of Cursor's own PRs now coming from cloud agents. Critical architectural decision: decoupling agent loop, machine state, and conversation state allows agents to run across different pod types and subagents to outlive parents. Another insight: as models improve, move logic out of the hardcoded harness into tools the agent controls (e.g., GitHub CLI, Playwright). The post also discusses current harness for computer use and future self-healing environments (autoinstall).

cursor.com · 11 min · Agent Architecture · Agent Infrastructure · Agents

07-02

Building a Good Vertical Agent: Context as a Cache Hierarchy

The article argues that a good vertical agent is a faithful compression of its task distribution, and its context should be organized as L1/L2/L3 cache tiers. Using their Shortcut spreadsheet agent as example, they detail extreme optimizations: reading a range compresses 500 formulas into a single legend line via R1C1 normalization and aliasing; after writing, a structured diff groups, samples, and triages changes, flagging #REF! errors under MUST FIX. L2 provides curated English specs fetched on demand, like the pivot table recipe that bakes in gotchas (suspendLayout/resumeLayout, raw integer 8 for aggregation). L3 is the raw API reference plus a 100-line grep skill that lets the model mine tens of thousands of lines in bounded steps. The prompt budget mirrors the frequency curve, and the hierarchy moves as models improve. Practical, transferable advice for engineers building reliable agents in any domain.

x.com · 21 min · Agent Architecture · Agent Infrastructure · AI Engineering

06-29

Temporary Cloudflare Accounts for AI Agents

Cloudflare introduces temporary accounts for AI agents, enabling deployment via `wrangler deploy --temporary` without manual signup. The accounts last 60 minutes, during which agents can iteratively deploy and developers can permanently claim them. The post addresses the problem of background AI sessions getting stuck at browser-based OAuth flows and explains how the CLI prompts agents about the flag for discovery. A complete TypeScript demo walks through deploying a hello world Worker, modifying it, and redeploying with verification. Partnerships with Stripe and WorkOS are noted as part of broader efforts to reduce agentic deployment friction. Target readers include agent platform builders and developers using coding agents.

x.com · 1 min · Agent Infrastructure · Agents · CLI

06-17

How to build a self-improvement loop for your Skills

This article demonstrates a practical approach to building a self-improvement loop for AI Skills using inner and outer agent loops. The inner loop triggers a cloud agent via GitHub Action on each new issue, applying a triage Skill to classify it. The outer loop runs daily, reviews all human corrections (label changes and comments), and generates a diff to update the Skill file, which is then merged back. The author uses Warp's Oz cloud agent platform for issue triage, providing complete code and a sample repo. The pattern is generalizable to code review, bug fixing, and incident response. Suitable for engineers building AI agents who want to improve skill quality over time.

x.com · 4 min · Agent Engineering · Agent Infrastructure · Orchestration

06-08

Every Agentic Engineering Hack I Know (June 2026)

The author shares 22 practical hacks for agentic engineering with Claude Code and Codex. The core is a plan-first workflow: use /ce-plan to generate a plan.md that guides the agent; humans skim or ask inline instead of reading it. Hacks include: voice input via Monologue or Wispr Flow (LLMs handle imperfect transcription); running 4-6 separate agent sessions in cmux tabs; defaulting terminal tabs to Claude Code and bypassing all permission prompts with sound alerts on completion; giving Claude an email address via AgentMail to trigger sessions remotely; using last30days before planning to search community discussions and news in parallel; turning repeated tasks into reusable skills to compound agent capabilities. He stresses that human value lies in providing taste and direction, not typing, and warns against AI addiction. The post is packed with copy-paste config snippets and concrete tools, aimed at engineers deep into AI-assisted development.

x.com · 28 min · Agent Infrastructure · Agents · AI Engineering