Topic
Source-linked workflows that name devtools. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
Coder’s blog shows wiring Microsoft’s VS Code Server into a Coder template so developers get browser VS Code with legal access to the Microsoft Extension Marketplace—including Copilot and Pylance—on cloud workspaces.
A Tencent Cloud community deep-dive shows installing CodeBuddy CLI via npm, logging in (WeChat or GitHub/Google), running codebuddy /init for a project map, then using natural-language Craft workflows aimed at pro/DevOps users.
Official Coder docs compare four ways to run Docker builds and tests inside container workspaces: Sysbox runtime, Envbox, rootless Podman, or a privileged docker:dind sidecar.
Official CodeBuddy MCP docs show how to add local or remote MCP servers with codebuddy mcp add, pick user/project/local scopes, approve project servers, and lock tools with mcp__server__tool allow/deny rules.
Coder admin docs let template owners set default autostop, activity bumps, and optional dormancy so idle workspaces stop (and eventually delete) instead of burning compute.
Official CloudBase docs show installing the CloudBase plugin (MCP + Skills) into CodeBuddy Code—or adding the MCP server by hand—so you can create apps, databases, functions, and auth from the CLI chat without opening the console.
Official Coder docs show four ways to reach apps running in a workspace—Coder Desktop auto-forward, coder port-forward CLI, dashboard Open Ports, or SSH -L—so you can hit web servers, Jupyter, and APIs on localhost.
Official CodeBuddy IDE deploy guide maps deliverable type to one-click Tencent Cloud paths—temp Cloud Studio preview, EdgeOne static CDN, CloudBase full-stack, or Lighthouse servers.
Coder’s tutorial walks you through a Docker+Ubuntu workspace template in Terraform: coder_agent, code-server via coder_app, persistent home volume, then push with the CLI or dashboard.
CodeBuddy IDE’s Figma2Code (via Craft Agent) lets you OAuth Figma, add selected components to chat, describe the stack, and preview generated UI code.
Short official blog on workspace anatomy: reproducible templates with deps/IDEs/config, plus connection options—web IDEs, SSH + VS Code Remote, or local file sync.
Three-iteration case study: starting from an MD/spec, using CodeBuddy in VS Code, then adding MCP so each step is verified—useful pattern for internal admin tools that must match official API docs.
Workshop write-up: define persona templates (cloud-native, serverless, agentic, GenAI) as Terraform, GitOps them, and run parallel agents each in isolated AWS workspaces instead of conflicting on one laptop.
End-to-end practice: open a Vue CloudBase template in CodeBuddy IDE, attach CloudBase MCP, authorize the cloud env, then generate user intake, financial profile charts, and planning flows with AI-assisted components.
Docs overview of Coder Agents, Agent Relay, IDE agents, and agents-in-templates—plus Terraform snippet to install Claude Code/Codex modules into a workspace template.
A builder documents building and launching Jieyou Baibaoxie ("worry-relief toolkit") using VS Code CodeBuddy plugin + CloudBase AI ToolKit MCP: install plugin, load AI rules, login to CloudBase, then generate multi-tool modules and iterate for review.
Coder blog explains why local Claude Code is risky for enterprises, then shows AWS/EKS reference setup, golden templates with Claude Code registry module, managed settings, and audited sessions.
Step-by-step practice: pick a Vue + CloudBase template, wire the CloudBase environment inside CodeBuddy IDE, then use natural-language prompts to add template CRUD, file upload, and cloud-function calls.
Official quickstart: install a container runtime, start coder server, create a Docker template in the template builder, launch a workspace, and connect VS Code Desktop or browser VS Code.
A Tencent Cloud developer-community guide walks through introducing CodeBuddy into a real R&D process: Plan/Design/Coding/Deploy agents, documentation-driven workflows, and team rollout tips based on internal usage.
An Indie Hackers founder almost shipped a no-auth “delete all users” endpoint Claude cheerfully wrote for a supposed test env—then built Thorim, a one-command layer of specialist agents/skills that makes coding agents challenge unsafe requests.
On HN, joshgachnang says Cursor Cloud Agents keep multiple workstreams going for his team, and computer use lets agents actually test features and show they work on PRs—alongside Bugbot as their best AI reviewer so far.
Product Hunt’s Pancake (“Vercel for GTM”) gives Claude/Codex a GTM Brain, 40+ enrichment providers, and sending infra via one MCP so founders can describe an ICP and let the agent keep finding and reaching leads.
Kelviq’s OpenClaw flow picks up Discord-tagged profile URLs, scrapes the site, checks policy, and returns approval/rejection with reasoning, category, and confidence—cutting manual MoR onboarding review.
Zachary Proser queues 5–7 maintenance, bugfix, and small-feature tasks each morning; Cursor background agents clone sandboxes, branch, and open draft PRs with ~70–80% one-shot success.
A developer routed Grok Bot through their ChatGPT Pro subscription after hitting cloud-agent limits, calling remote Codex environments clunkier than Cursor but workable.
A founder spun up nine Grok Bot agents plus an orchestrator sharing one Obsidian vault on xAI Premium; after he approved, an agent purchased domains with his credit card and he went back to his weekend.
Parallax is a Windows/Linux desktop workspace that runs Claude Code, Codex, Antigravity or any shell in named panes with a built-in editor, local Git, session directory, voice chat, and saved layouts—agents stay independent (no auto-orchestration); local-only data; subscription required ($11.99/mo or $99.99/yr USD) plus your provider plans.
Tern is a free closed-source Mac-native (CLI/TUI also on Linux) control plane for 16 coding-agent CLIs: each task gets its own git worktree/branch, changes land in one review queue with comments routed back to the agent, conflict radar, multi-step runs with gates, phone approvals without Tern servers, and a daemon that keeps agents alive after you close the window.
MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
Replit Bring Your Own Cloud (Oct 16) deploys cellular Replit—including the Agent harness—into enterprise Azure/GCP/AWS tenants: Full BYOC (private preview) for platform+apps in-tenant, BYOC for Published Apps (early access) for publish destinations with CMEK/tunnels, and Image Exports (Docker+Terraform+SBOM) for air-gapped self-host.
Local-first Apache-2.0 CLI for Claude Code/Codex/Cursor: mcp-xray ranks bloated tool schemas, sync compresses CLAUDE.md↔AGENTS.md↔Cursor rules, and shield fails CI on leaked keys/prompt-injection/Trojan Unicode—claims large cuts in model-visible prompt size without API calls.
AGPL self-hostable workspace runs Claude Code, Codex, OpenCode or Pi in isolated sandboxes; hand off from Slack/web/API, attach playbooks/skills/knowledge, approve sensitive actions, and get PRs or files back—positioned as an open Devin alternative.
Apache-2.0 agent-native sandbox (Linux FUSE/Landlock, macOS APFS clones+Seatbelt) gives agents a confined FS view with unified text diffs, binary markers, and per-task or per-tool-call commit/abort—optional JSON-RPC adapters for Pi and policy for secrets/network.
Mirror is Reflection's early-beta coding agent for the terminal—defaults to Beam-1.0-501B-A23B, manual/auto tool approval, resumable conversations, parallel /worktree agents, AGENTS.md+skills+MCP/extensions, with provider keys kept out of the agent's shell environment.
Hosted Speko MCP (mcp.speko.ai, 101 tools) lets Claude Code/Codex/Cursor create, deploy, roll back and eval voice agents, manage sessions/calls/phone numbers/knowledge bases, and migrate external configs—directory hosts expose narrower, safer tool surfaces.
Installable Claude Code pack (/launch-check) runs 440 read-only checks across security, payments, DB, SEO and AI tool permissions, then scores the app and lists file:line fixes; optional /launch-fix applies worst-first patches you review.
Apache-2.0 Paseo runs Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity, and Muse Code in isolated worktrees from desktop, native mobile, or remote hosts—with MCP/CLI/SDK automation, plugins, and optional E2E-encrypted relay so you steer agents without changing their subscriptions.
Open-source stdlib-only dashboard on 127.0.0.1 merges Claude Code, Codex, Cursor, Gemini CLI, and Antigravity chats: surfaces questions/permissions/limit stalls, shows 5h/7d usage per account, and lets you reply without burning tokens just to look.
MIT-local Python skill/CLI/dashboard coordinates Claude Code, Codex, and Cursor on one project: shared registry, ack-before-work, prove bound to file fingerprints, independent (non-author) review, and cross-provider usage/balance so green tests on the wrong code cannot close a task.
Confidee/flowreel (Apache-2.0 Claude Code plugin) turns deterministic Playwright flows into captioned, narrated demo videos with a dev-then-staging release gate—assertions decide pass/fail; Claude writes/explains flows but does not judge them.
Open-source mcp-router sits between Claude Code and many MCP servers: find_tools / call_tool / run_script stand in for hundreds of tools; on a 441-tool fleet vs six other proxies it finished 6/6 tasks at −29% tokens while peers often used more tokens or failed—Show HN + public BENCHMARK.md.
Thenovi AI (Band) launched a desktop app plus CLI so engineers can see fleets of coding agents at once—projects, ownership, blockers, questions, progress—and intervene without manually shuttling session context between isolated harnesses.
Open-source CLI+MCP (morluto/rea) lets Claude Code/Cursor inspect binaries, Electron/.NET/apps via Hopper/Ghidra/IDA, returning evidence-backed observations so agents can rebuild features from behavior without copying source.
macOS menu-bar app that finds npm/dev servers and daemons started by Claude Code, Cursor, Codex, OpenCode, or T3 Code—including ghosts after the agent exited—and kills the process tree in one click.
Thesys’s OpenUI hit 1.0 (Oct 15): models stream OpenUI Lang into your registered React components (cards/forms/charts); Lang 1.0 adds defineAction/defineFunction, library.extend, and stored messages; CLI scaffolds apps and setup-agent writes AGENTS.md for Claude Code/Codex/Cursor—vendor tiktoken bench claims ~53% fewer tokens vs JSON-render formats.
Microsoft Copilot Studio adds org-owned managed agents with their own Microsoft 365 credentials (@mention in Teams/Outlook/Office comments), business process memory that carries preferences across cycles, and GitHub Copilot harness triggers so agents start on email or a cadence without a new prompt—rolling out via Frontier.
@GitHub in Slack and Microsoft Teams can now answer across multiple repositories in one thread—open PRs, weekly merges, cross-frontend/backend investigations—plus use shared Slack thread context without copy-paste.
OpenAI Codex 0.163.0 lets you send a follow-up while it is still answering (interrupt also stops Code Mode cells/tool calls), adds searchable live /config, parallel skill/memory/history reads, and Daybreak-by-default for eligible accounts.
GitLab 19.5 makes the MCP server GA on Free/Premium/Ultimate: Claude Code, Cursor, Codex and other MCP clients get consolidated tools (get_merge_request, get_pipeline) plus Duo Agent Platform flow handoff under existing GitLab permissions, with GitLab.com rate limits of 60/min Free and 600/min paid.
Anthropic’s PR Code Review left research preview: auto-reviews on new GitHub PRs in ~6–10 minutes, with Quick/Standard/Deep intensity per repo for Team and Enterprise.
Enterprise GA for cg-oci, cg-apk, cg-versions, and cg-api so Claude Code/Cursor agents verify image tags, Wolfi package equivalents, EOL status, and org policy/attestations via browser OAuth or chainctl—server-side caps instead of prompt guardrails.
Official Pantheon MCP lets Claude Code/Cursor/Desktop inspect workspaces, sites, environments, builds, deploys, runtime logs, upstreams and secrets under your Pantheon identity; reads by default, state-changing tools pause for explicit approval; no deletes in beta.
Single Rust binary indexes calls/imports with tree-sitter, stores project/session memory in one SQLite file, and serves cited line-anchored excerpts over MCP—setup wires Claude Code/Codex/Cursor; reported 3–22× faster extracts vs Graphify on 13 codebases.
Octopus Cloud ships a built-in HTTP MCP at /mcp so coding agents can list spaces/projects, check PR deployment status, create/promote releases, run runbooks, search task logs and audit events—no per-machine local MCP to install; Server gets it in 2026.3.
Anthropic rebuilt monorepo source control as Scion after merges rose from ~2,500/day (May) to 30,000+/day (Sep): server-side commits/merges/blame, sparse/virtualized checkouts, API queries without local clones—200× smaller infra than git mirrors; Scion itself is internal, but the post is a learnable blueprint for agent-era VCS.
ExcaliClaw’s hosted Streamable HTTP MCP (https://excaliclaw.com/mcp) lets Claude Code/Desktop, Cursor, Codex, VS Code, OpenCode and OpenClaw list/create/update diagrams, ER/flowcharts, collections, PNG/SVG export, and live canvas collab under browser OAuth—unlimited MCP on all plans; launched on Product Hunt around Oct 12, 2026.
Stable open-source Azure MCP 3.0 adds Backup, Resilience, SRE Agent, Terraform/Advisor, Monitor/Cosmos/IoT toolsets plus clearer schemas, --learn, and secure-by-default resource creation so Copilot/Cursor/Claude agents can inspect and plan Azure work with predictable contracts.
Apache-2.0 terminal/VS Code/Zed agent (ACP) runs commands under Seatbelt/bubblewrap so writes stay in project+temp+caches, network is closed unless allowlisted, edits ask first, team policy can't be loosened by a cloned repo, and an outside hash-chained audit log verifies with /audit verify.
Functionize ships an MCP server so Claude Code/Cursor/Copilot hand change context to Studio, which builds/runs smoke or regression suites against the live app and returns the first failing step in-chat—closing the gap where agents never saw the product run.
LiteLLM open-sourced Moyai—the Devin-like cloud agent they run in production: Slack/browser tasks get isolated cloud workspaces (terminal+FS+browser), run Codex/Claude Agent SDK/Hermes/OpenCode, open PRs, and attribute spend through your LiteLLM gateway (they estimate ~79% lower vs their Devin bill).
OutSystems MCP is GA on every ODC tenant: Claude Code/Codex/Cursor/Kiro can hand work to Mentor for apps/agents/workflows/libraries, query the estate, publish/promote/roll back, and keep ODC roles, approvals and audit—install from github.com/OutSystems/outsystems-mcp.
Remote MCP at anaconda.com/api/mcp returns package facts, curated CVEs, org channel policy, and forum hits so Claude Code/Cursor/Codex/Kilo check real conda names and vulns before proposing installs—server cannot mutate your machine; agent still runs conda under your permissions.