Skip to content
UsecaseBoard
Saved0

Tool

Claude Code use cases: 109 examples

Source-linked workflows that name Claude Code. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.

codersponsor

Pick the right way to run AI coding agents on Coder

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.

CoderCoder AgentsClaude Code+1
Source ↗
codersponsor

Run Claude Code safely inside governed Coder workspaces

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.

CoderClaude CodeAWS EKS+1
Source ↗
webAgent-Harness

Run coding agents on a disposable VPS—one Linux user per agent

A Lobsters-linked write-up: isolate Claude Code/Codex-style harnesses on a cheap Hetzner VPS with named users (vikki/clara/…), tmux sessions, a shared bot GitHub account, and disposable machines so yolo-mode stays off your laptop.

Claude CodeCodextmux+1
Source ↗
indiehackersClaude-Code

Thorim makes Claude Code and Cursor push back on dangerous asks

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.

ThorimClaude CodeCursor
Source ↗
hackernewsClaude-Code

Kelos runs Claude Code and Codex in K8s pods that retry when CI fails

Kelos orchestrates Claude Code, Codex, Gemini, or OpenCode in ephemeral Kubernetes pods as CRDs—watching bug issues, drafting fix PRs, self-reviewing, and retrying when CI fails—while the author still does final review and merge.

KelosClaude CodeCodex+1
Source ↗
hackernewsCI

CircleCI Chunk sidecars validate agent code in microVMs before CI

CircleCI's Chunk sidecars run scoped microbuilds in Firecracker/E2B microVMs that mirror CI, hooking agent stop/eval events so Claude Code, Codex, or Cursor changes are validated before commit—~27s microbuilds and 3–5× lower token burn on retries in their tests.

ChunkClaude CodeCodex+2
Source ↗
hnCursor

Split Cursor for focus and Claude Code for parallel CI agents

A developer using both daily reports code quality converging once plans are clear, but keeps Cursor for slow focused diffs/sense-making and Claude Code for parallel/async agents plus well-scoped CI/CD tests and refactors.

CursorClaude Code
Source ↗
webClaude-Code

Claude Code manages Home Assistant automations via MCP

Adam keeps HA automations in git; Claude Code uses an MCP server to search entities, read traces, edit YAML, scp to the hub, reload, and commit—fixing a noisy camera automation in under two minutes.

Claude CodeHome AssistantMCP
Source ↗
githubMCP

subagent-reuse MCP: stop Claude Code subagents re-reading the same files

Show HN: `npx subagent-reuse --setup` adds an MCP that scans ~/.claude/projects/, builds SHA-256 Merkle trees of files each subagent already read/modified, and route_task decides REUSE vs CREATE_NEW before spawn—structural overlap only, no embeddings; ~1k LOC JS + 52 tests.

subagent-reuseClaude CodeMCP
Source ↗
githubMCP-security

RugSnare: pin MCP tool contracts and catch silent drift

Show HN (Oct 17): RugSnare pins each MCP tool's {name, description, inputSchema} by canonicalized SHA-256 at install, then diffs upgrades across 24 popular servers (~3.6M weekly installs)—336 contract changes found; grades BREAKING/LOOSENED/EXPANDED/NOTATION/COSMETIC and exits 1 for CI. Apache-2.0, zero npm deps; OWASP MCP Security Cheat Sheet now recommends contract pinning.

RugSnareMCPClaude Code+2
Source ↗
productcoding-agent

Parallax: paid desktop workspace for Claude Code/Codex side by side

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.

ParallaxClaude CodeCodex+1
Source ↗
productcoding-agent

Tern: free native fleet IDE—one worktree per agent, one review queue

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.

TernClaude CodeCodex+3
Source ↗
githubobservability

Tracekit 1.2.3: tamper-evident flight recorder for AI agents

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.

TracekitClaude CodeOpenAI Agents+3
Source ↗
productobservability

Agent Standup: live animated call for Claude Code / Codex / Vibe sessions

Agent Standup (OSS, local) turns Claude Code, Codex, Mistral Vibe, and Cowork sessions into a live stand-up: desks, screen-share of real commands/diffs, voices, replay + recap; `npx @double_geste/agent-standup --open`; VS Code/Cursor extension and Claude Code plugin. Free; optional Halloween character pack from €2.

Agent StandupClaude CodeCodex+2
Source ↗
docsMCP

PreReason MCP: dated market context so agents stop inventing numbers

Show HN / docs (Oct 16): PreReason MCP (`npx @prereason/mcp`) gives Claude Code/Cursor/Muse pre-reasoned markdown briefings and metrics—33 briefings, 293 metrics, source-dated figures—so agents reason over attributed market context instead of undated guesses; free tier + OAuth/agent claim flow.

PreReason MCPClaude CodeCursor+2
Source ↗
productMCP

Things to Do API MCP: local events knowledge base for agents

Show HN (Oct 16): Things to Do ships REST + HTTP MCP so agents query SF Bay Area shows, pop-ups, concerts, and festivals in plain language (`claude mcp add --transport http thingstodo https://api.thingstodoapi.com/mcp`) instead of slow web search or ad-hoc scraping; NYC/LA listed as soon.

Things to Do APIMCPClaude Code+1
Source ↗
productmath

Lemma Park: Folding@home-style math lab for coding agents

Lemma Park (Show HN ~12h): paste join.md / install.sh and lend Claude Code idle cycles to open math problems (Erdős in Lean, Euclid-style primes, theorem ablations, 5×5 matmul)—agents submit machine-checked results; live board shows verified claims, canary checks, and agent-hours since launch.

Lemma ParkClaude CodeLean+1
Source ↗
blogMCP

Summer Engine MCP + CLI: agents build and ship games

Summer Engine (Oct 16) ships hosted MCP (https://mcp.summerengine.com/mcp), local `summer mcp`, and a full CLI so Claude Code/Codex/Cursor can generate assets, drive the engine, publish store pages, and pull analytics—`summer_search`/`ops search` map plain language to exact ops; CLI-only setup via skills with `--dry-run`/`--json` for safe agent scripting.

Summer EngineSummer MCPSummer CLI+3
Source ↗
githubcoding-agent

Weatherdeck: read-only status board for AI coding-agent lanes

Show HN Weatherdeck (Oct 16): a read-only TV/phone status board fed by small pushers that shows which coding-agent lanes are waiting on you, honest progress ranges, silent sources, and deferred/owned work—not monitoring/alerts; demo mode with ship-deck theme; open source on GitHub.

WeatherdeckClaude CodeCodex
Source ↗
docsagent-tools

DeepSeek Search & Fetch APIs: standalone web tools for agents at $0.75/1k

DeepSeek shipped standalone Search (`POST /v1/tools/search`) and Fetch (`POST /v1/tools/fetch` → Markdown) APIs for agents/RAG: $0.75 per 1,000 successful requests each (empty/failed free); Claude Code built-in Web Search and Codex `web_search` waive Search fees for the first two weeks after launch, then standard pricing—docs live under Search & Fetch on api-docs.deepseek.com.

DeepSeek Search APIDeepSeek Fetch APIClaude Code+1
Source ↗
githubcoding-agent

XERJ: autoindex + MCP so coding agents search folders without grep waste

XERJ is an Apache-2.0 Rust single-binary AI-native search engine: `xerj autoindex` turns code/docs/logs/PDFs into ES-compatible indices; `xerj init` registers MCP + a short skill for Claude Code/Cursor; agents get passage search, hybrid retrieval, and namespaced memory instead of dumping whole files—trending hard on GitHub (~7k stars) with agent-oriented llms.txt.

XERJClaude CodeCursor+1
Source ↗
hnMCP

CtxWise: MCP schema tree-shaker and context firewall

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.

CtxWiseClaude CodeCodex+2
Source ↗
productcoding-agent

UseAgent: open-source shared workspace for Claude Code/Codex/OpenCode/Pi

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.

UseAgentClaude CodeCodex+3
Source ↗
productMCP

Kerno: local runtime QA that verifies agent changes against your stack

MCP-connected runtime QA maps critical flows and entry points, then re-tests the blast radius of each Claude Code/Cursor/Codex change against live Postgres/Kafka/APIs/MCP tools—contracts, authz, OWASP, errors—before merge, with self-heal when behavior changes on purpose.

KernoClaude CodeCursor+3
Source ↗
productmulti-agent

Bandito: Mac crew that runs Claude Code/Codex/Grok on your servers

Native macOS app orchestrates official Claude Code, Codex and Grok CLIs as a role-based crew (lead/builder/reviewer/docs/auditor/on-call) on your Mac or VPS with schedules, one-click risky-command approvals (Telegram too), and server screen/browser/terminals—no Bandito cloud for your code.

BanditoClaude CodeCodex+1
Source ↗
docsMCP

Speko MCP: build and operate voice agents from the coding agent

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.

Speko MCPClaude CodeCodex+3
Source ↗
productlaunch-checklist

LaunchReadyKit: 41 Claude Code agents audit launch readiness

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.

LaunchReadyKitClaude Code
Source ↗
productorchestration

Paseo: cross-device control plane for many coding agents

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.

PaseoClaude CodeCodex+4
Source ↗
productmulti-agent

DHI Orbit: one local board for every coding-agent chat

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.

DHI OrbitClaude CodeCodex+3
Source ↗
githubmulti-agent

Squadra: source-bound proof for multi-window coding agents

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.

SquadraClaude CodeCodex+2
Source ↗
xdevtools

FlowReel: Playwright E2E flows become narrated product demos

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.

FlowReelClaude CodePlaywright
Source ↗
otherself-hosted

Agenvoy: self-hosted 24/7 personal agent that auto-builds MCP tools

Taiwan-built open-source Go daemon runs on your machine (memory/schedules/credentials stay local): if a tool is missing it writes, sandbox-tests, and registers one, then shares the library with Claude Code/Codex via MCP server mode—alternative to cloud VM agent products.

AgenvoyClaude CodeCodex+2
Source ↗
othercontext-compression

SuperCompress: query-aware context cut for coding agents

SuperCompress v2 compresses context against the query (keeps answer-critical lines verbatim): ~64% mean cut on their B5 coding-agent suite with 24/24 evidence-retention passes; MCP/plugin for Cursor/Claude Code/Codex plus hosted API and open weights.

SuperCompressClaude CodeCursor+2
Source ↗
hnmcp

mcp-router: search+lazy MCP proxy that actually cut tokens

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.

mcp-routerClaude CodeMCP
Source ↗
hnmobile

PocketConsole: run Claude Code on your server from iPhone

iOS app that remotes into your own Claude Code host so you can kick off tasks, approve steps, watch live previews/terminal, and keep progress from your phone—self-hosted control plane, not a cloud sidecar.

PocketConsoleClaude CodeiOS
Source ↗
hnworkflows

AI-DLC: adaptive workflow steering rules for coding agents

AWS Labs open-source (5k+★): one harness-neutral core turns Claude Code/Codex/Cursor/Copilot/Kiro/opencode into structured, verifiable delivery workflows via `aidlc config --harness` + doctor—install script, not a new agent.

AI-DLCaidlcClaude Code+5
Source ↗
othermulti-agent

AgentPrism: JS workflow scripts over real coding-agent harnesses

SDK + stdio MCP server run agent()/parallel()/pipeline() scripts that fan out to Claude Code, Codex, OpenCode, or pi via ACP, with journaling, resume, and git-worktree isolation.

AgentPrism@automatalabs/workflows@automatalabs/mcp-server+5
Source ↗
hnmulti-agent

Beeline: multiplayer room for humans and coding agents

Open team chat where you @-mention Claude Code/Codex/Pi/Goose in one Room; agents open corners to plan/build/test and bring a single approve-merge decision—multiplayer harness instead of single-player agent sessions.

BeelineClaude CodeCodex+2
Source ↗
hnmemory

Busabase: system of record for AI agent work

Local-first OSS DB/workspace where Claude Code/Codex/Cursor share durable records, docs, skills, and apps—writes that matter go through human review; Skill, MCP, OpenAPI, and ACP connections keep agents stateless and work durable.

BusabaseClaude CodeCodex+3
Source ↗
githubcoding-agents

Hopper HQ: office dashboard for Claude Code sessions

Local-first npm app: isometric office UI where each Claude Code session gets a desk; red windows flag waits for you, with tmux integration—watch many agents without scrolling terminals.

Hopper HQClaude Codetmux
Source ↗
hnagent-memory

MuscleMemory: test-gated procedural memory for coding agents

Open-source local procedural memory that learns only after tests pass, then hands Claude Code/Codex/Cursor a short verified skill note on similar tasks (reported token/tool cuts in published benchmarks).

MuscleMemoryClaude CodeCodex+2
Source ↗
xmcp

REA: one MCP for agent reverse engineering (binaries to apps)

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.

REArea-agentsClaude Code+4
Source ↗
githubcoding-agents

Reaper: kill orphan processes coding agents leave behind

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.

ReaperClaude CodeCursor+3
Source ↗
githubmemory

Renor: Markdown memory for coding agents over MCP

OSS (AGPL): index a folder of Markdown notes into local SQLite, then expose search/recall/remember tools over MCP so Claude Code/Codex reuse decisions across sessions; hosted option at renor.cloud.

RenorMCPClaude Code+2
Source ↗
hncontext-window

context-tax: price what Claude Code sends before you type

CLI reads Claude Code transcripts to show per-turn context cost—what ships before the first keystroke, unused payload, and skills that never reached the agent—so you can trim defaults instead of guessing.

context-taxClaude Code
Source ↗
hnagent-security

heldkeys: list credentials your coding agent can reach

Read-only CLI that inventories env/CLI/.env/MCP/SSH/cloud logins an agent inherits on laptop, sandbox, or CI—and flags risky agent steps in GitHub Actions—without printing secret values.

heldkeysClaude CodeCodex+2
Source ↗
githubgenerative-ui

OpenUI 1.0: MIT generative UI runtime so agents render interfaces not text

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.

OpenUIOpenUI LangClaude Code+3
Source ↗
blogmcp

GitLab MCP server generally available in 19.5

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.

GitLab MCPClaude CodeCursor+3
Source ↗
blogsafety

OpenRouter Armor: plain-English classifier for agent tool calls

Beta plugin sits between the model and your app: write hard-deny/soft-deny/allow rules in prose; Armor evaluates every tool call (powered by a decision model) and blocks policy violations before bash/git/exfil runs—Claude Code auto mode works via Ori on any OpenRouter model.

OpenRouter ArmorJevClaude Code+2
Source ↗
blogmodel-release

Claude Opus 5.5 fast mode: GA without waitlist

Anthropic took Opus 5.5 fast mode out of research preview: set `speed: "fast"` (no beta header) for up to 2.5× OTPS at $8/$40 per MTok; separate rate limits; Claude Code `/fast` for interactive loops.

Claude Opus 5.5Claude APIClaude Code+1
Source ↗
blogproduct

How Codex Happened: inside OpenAI's coding-agent comeback

Oct 15 Every deep dive (Shipper + six OpenAI interviews): Cloud flop → Rust local agent → no-editor desktop app → ChatGPT merge; learnable arc on form-factor bets, separate model lines, and agent-native UX.

CodexChatGPT desktopGPT-5.x Codex+1
Source ↗
blogcode-review

How the Claude Code team reviews agent-written PRs

Anthropic’s Claude Code team documents a layered review stack—pre-PR verify, AI review + security block, risk-tiered human approvals, merge queue/flags, and fast rollback—so most agent PRs merge with ≤1 human while revert rate fell >40% as volume doubled.

Claude CodeClaude Code ReviewREVIEW.md+2
Source ↗
bloglearnable-paradigm

What 1,866 GitHub projects tell their AI coding agents

Empirical study: 34% of popular active repos ship agent instruction files (AGENTS.md dominant); half exceed ~100 lines; ~3/5 rules could be script-checked but <1/20 name the check—actionable lint: short map, name enforcers, one rulebook.

AGENTS.mdCLAUDE.mdCodex+2
Source ↗
blogMCP

AISLE MCP + package firewall: prove, fix, and block in the IDE

AISLE October rollout (Oct 14): MCP server puts exploit-proven findings into Claude Code/Cursor so agents fix in-editor; plus an AI package firewall that intercepts npm/PyPI/Cargo installs from humans and coding agents, with cooldown and monitoring mode before enforcement.

AISLE MCPClaude CodeCursor+1
Source ↗
company-blogMCP

NeuBird ARC GA: governed production ops with IDE MCP

Agentic Reliability Center GA gives one metered telemetry+LLM door, shared operational memory, and human-in-the-loop policy gates; new MCP lets Claude Code/Cursor/Codex investigate incidents from the IDE while inheriting audit trails and approval gates.

NeuBird ARCNeuBird MCPClaude Code+3
Source ↗
company-blogMCP

Chainguard MCP GA: four OAuth servers for agent dependency checks

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.

Chainguard MCPcg-ocicg-apk+5
Source ↗
company-blogMCP

Pantheon MCP Server public beta: fleet ops from coding agents

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.

Pantheon MCPClaude CodeClaude Desktop+2
Source ↗
githubcode-intelligence

Graphicle: Rust code-graph + memory MCP for coding agents

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.

GraphicleMCPClaude Code+3
Source ↗
otherteam-agents

Merlin: run Claude Code and Codex from Slack, Linear, and GitHub

Merlin dispatches team asks from Slack/Linear/GitHub to Claude Code or Codex already signed in on teammates’ machines—reuse local repos, MCP servers, and skills with no extra model API bill; results return in the same thread, with shared skills, schedules, and workspace memory.

MerlinClaude CodeCodex+4
Source ↗
huggingfaceopen-model

inclusionAI Ling-3.1-flash: 560B MIT hybrid MoE for agents and coding

inclusionAI/Ant Ling open-sourced Ling-3.1-flash (560B total / ~25B active, 1M context, MIT) for agents, office, search, and SWE—day-0 SGLang/vLLM recipes, tool/reasoning parsers, and strong Terminal-Bench / SWE-bench Pro / SkillsBench numbers; works in Claude Code, Hermes, OpenClaw, and related harnesses.

Ling-3.1-flashSGLangvLLM+2
Source ↗
company-blogMCP

Octopus remote MCP: deploy/operate without a local install

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.

Octopus DeployMCPClaude Code+2
Source ↗
blogdesign-agents

MagicOS: PRD-to-UI canvas that hands winners to coding agents

Magic Patterns’ MagicOS is an infinite canvas for PRDs, GitHub context, screenshots, and side-by-side UI variants; pick a winner and hand it to Claude Code, Cursor, Codex, or any MCP-compatible coding agent instead of losing the design journey in a linear chat log.

MagicOSMagic PatternsClaude Code+3
Source ↗
productMCP

Pensieve: local MCP index so agents stop grepping the whole disk

HN (Ted Haley): Pensieve locally indexes code, docs, and past agent sessions (watches repos/worktrees/uncommitted edits), exposes MCP search so Claude Code/Codex/Cursor get the few relevant passages with file:line instead of multi-round grep; Qwen3-Embedding-0.6B + SQLite/trigram + turbovec; macOS-focused OSS.

PensieveClaude CodeCodex+2
Source ↗
productagent-sandbox

Agent37 (YC F26): low-cost gVisor sandboxes for agent harnesses

Launch HN: Agent37 hosts Hermes/OpenClaw/Claude Code/Codex/OpenCode/Pi (or your Docker) in per-tenant gVisor sandboxes; prepaid compute meters by the minute (2 vCPU/4 GB ≈ $4.76 for 730 awake hours), disk-only when asleep (~$0.36/mo for 4 GB), $5 starter credit, free personal tier, managed MCPs + LLM gateway; avg customer spend cited at $0.37/sandbox/mo.

Agent37HermesOpenClaw+4
Source ↗
product-huntMCP

ExcaliClaw MCP: hand-drawn diagrams agents can create and edit

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.

ExcaliClawMCPClaude Code+3
Source ↗
githubmulti-agent

CLI-Dispatch: Claude Code delegates to Codex/Gemini/DeepSeek in worktrees

MIT Claude Code plugin hands tasks to DeepSeek, Gemini (Antigravity), Codex, OpenCode or Copilot as worker CLIs—each in an isolated git worktree with your verify command—then returns a compact verdict/patch for Claude to review; API keys stay in a local browser form.

CLI-DispatchClaude CodeCodex+4
Source ↗
productagent-isolation

Abyss: Docker+WASM middleware isolation for ACP coding agents

Show HN: Abyss runs Pi/Hermes/Claude/Codex (any ACP agent) in Docker with path-aligned mounts, then applies host WASM plugins that can redact secrets, hydrate RAG, inject MCP, or auto-cancel sessions—agent-agnostic harness features without rewriting each agent plugin.

AbyssACPPi+4
Source ↗
blogMCP

Functionize MCP: Studio app context for coding-agent tests

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.

Functionize MCPFunctionize StudioClaude Code+2
Source ↗
company-blogMCP

OutSystems MCP GA: build, ship, and operate ODC from your coding agent

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.

OutSystems MCPMentorClaude Code+4
Source ↗
producthuman-in-the-loop

Reright: MCP review queue so agents send only text you approve

MCP server plus local hooks route agent-written commits, PR text, emails and support replies into one editable queue; you rewrite and approve, then the agent sends exactly your version—Claude Code tested; Codex/Gemini/Copilot/Cursor installer-configured; free tier then paid.

RerightMCPClaude Code+4
Source ↗
company-blogMCP

Anaconda MCP GA: remote read-only package facts for agents

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.

Anaconda MCPKiloClaude Code+3
Source ↗
blogMCP

LaunchShots MCP: App Store screenshots from your coding agent

LaunchShots MCP lets Claude Code/Cursor/Codex/Gemini CLI capture key screens, draft store copy from the README, and return an editable App Store / Play screenshot set in ~1–2 minutes—one-line Claude install; free daily allowance without an API key, then credits or Launch Kit plans.

LaunchShots MCPClaude CodeCursor+2
Source ↗
productagent-security

OpenAPPA: deterministic flow-label guardrails that don't break agents

Open-source MIT guardrail tracks audience×trust labels across tool calls (algebra, not LLM-as-judge), returns remedy plans (sanitize/authority/subagent) so agents keep ~90% task completion with 0% exfil on their benches—plugs via pre/post tool hooks; docs also as MCP.

OpenAPPAClaude CodeMCP
Source ↗