Castforge
Castforge is a desktop workspace that runs a configurable team of AI coding agents (Lead, Coders, Tester, Reviewer, Designer, etc.) to plan, build, test, and review software projects locally while you steer the work.
Castforge is ai agents software teams evaluate for software & gaming. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: Software & Gaming
What it does
AI Agents software for decision-makers comparing workflow fit and alternatives.
Best fit
Software & Gaming
Pricing snapshot
Pricing available from Free during early access
Next step
Compare Castforge with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Castforge
Castforge is a desktop workspace that runs multiple AI coding agents in distinct roles (Lead, Coders, Tester, Reviewer, Designer, etc.) to automate planning, implementation, testing, and review of software projects while keeping the human user in control. It is aimed at developers and teams who want a guided, review-first multi-agent workflow, live previews, and local project control. The product is distributed as a downloadable Windows app (v0.6.7-beta) with macOS and Linux builds coming soon, and is free during early access.
Castforge runs Claude Code, Codex, Gemini and GitHub Copilot as one reviewed AI dev team on a live board you steer. Free during early access. Windows.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
Multi-agent teams
Run configurable teams of agents in real roles (Lead, Coders, Tester, Reviewer, Designer, Researcher). Assign roles to agents and pick the model per seat; presets (Solo, Pair, Trio) speed onboarding.
Bring-your-own-AI / Sign-ins
Sign in with GitHub Copilot for a free start, connect Claude, ChatGPT/OpenAI, Google Gemini, or paste your own API key. Connect subscriptions you already pay for; requests go from your machine to your provider.
Live preview & Time Machine
See your app render live with desktop, tablet, and phone frames. Time Machine lets you scrub through snapshots and pick up from prior points.
Course/Phase board (project board)
A Lead drafts a phase board for each project; cards move as the team works, dependencies are enforced, and you can group phases into milestones and reorder the backlog.
Adaptive intent routing
Messages are analyzed for intent and handled at the appropriate depth — quick fixes run immediately, larger requests trigger full plans and the whole team; chat announces depth with a one-click override.
Project memory & append-only ledger
A living summary of every project (stack, what's built, key decisions, invariants, current focus). Every agent reads this before touching work. History is stored in an append-only ledger and can be exported to a decisions.md file.
Quality and review gates
Built-in quality tiers decide which review gates run (plan-check before code, goal-backward verification against acceptance criteria). Three tiers from Draft to Max, with skipped gates reported explicitly.
Self-healing runs
Detects when a step did not actually produce the expected output, names the issue, attempts a repair once, and reports the result rather than silently accepting or hiding failures.
Backend scaffolding
Prebuilt guided setups for common backend pieces: Auth (sign-in, sessions), Database (schema, migrations), Payments, Email, File storage, Scheduled jobs, and a test harness.
Isolated seats and permission modes
Each agent seat runs in an isolated home; read-only seats are enforced per seat (they do not receive connected servers). Permission modes include Careful, Balanced, and Autonomous.
Parallel branches and merge gates
Run multiple agents in parallel, each on its own branch/worktree, then merge with a review gate and enforcement of dependencies.
Integrations
Wire in GitHub, Vercel, and Supabase from setup so agents can use them during runs.
Pricing
Castforge is free while in early access. You bring your own AI; each provider bills you directly for model usage.
Early access (free)
Free during early access- Download and use Castforge free during early access
- Bring your own AI sign-ins or API keys; providers bill you directly
- Access to multi-agent workflows, project boards, live preview, and backend scaffolding
Use Cases
Accelerate web app development
Let an AI team plan, scaffold the backend, implement features, run tests, and prepare publish drafts so developers can iterate faster with guided scaffolding for auth, DB, payments, email, storage, and scheduled jobs.
Automated code review and QA
Use Reviewer and Tester roles plus quality tiers and verification gates to catch weak plans and verify delivered work against acceptance criteria automatically.
Orchestrate multiple AI providers
Combine sign-ins and API keys from providers you already pay for (Copilot, Claude, OpenAI, Gemini, Cursor, local models) to run the best agent for each role without per-token billing from Castforge.
Maintain project continuity and audits
Keep a decision ledger and project memory so context survives restarts, new agents, or crashes; export decisions.md to commit alongside code.
Live-preview driven UI development
Watch the app render live for desktop, tablet, and phone while a Designer role reviews the UI against a design spec.
Integrations
GitHub
Connect GitHub for repository access and workflows.
Vercel
Wire in Vercel as a publishing/deployment target (publish to web coming soon).
Supabase
Connect Supabase as a backend/data service from setup.
AI providers (sign-ins and API keys)
Sign in with GitHub Copilot, Claude, ChatGPT/OpenAI, Google Gemini, Cursor, or paste API keys; local models supported.
Benefits
Limitations
Frequently Asked Questions
Do I need an API key?
Does my code leave my machine?
What does Castforge cost?
Which agents work?
Is there a macOS or Linux version?
Can my team use it together?
Getting Started
- 1 Step 1: Download the Windows build (v0.6.7-beta) and sign in — the fastest start is a free GitHub Copilot sign-in.
- 2 Step 2: Open an existing project or start fresh; the Lead will suggest a team and draft a plan for you to review before anything runs.
- 3 Step 3: Approve the single offered action to begin runs, then watch the board, preview the app live, and steer or approve work as it proceeds.
Support
Discord
Public Discord for feedback and beta discussion; the founder reads it.
Docs
Product documentation available from the site (Docs link).
Changelog
Changelog on the site for release notes and beta updates.
Contact
Contact page linked from the site for inquiries.
API
Compare Castforge with similar tools
See how it stacks up against alternatives
Related Tools
View all 522 →
Needle2
Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.
The cheapest GPU cloud
Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.
Oodle.ai
Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.
Nous
Nous is an open-source context graph for agentic GTM (go-to-market) teams that centralizes identity-resolved people and company data from multiple GTM tools so agents can read a single, source-traced account context in one call. It is available as a hosted service and as a self-hostable stack.
Premium Alternatives
AletheionAGI
AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.
ClaudeThings
ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code — delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.
Sitemanagerai
Site Manager AI is a web + iOS app that provides UK construction site managers and foremen instant, regulation-aware answers, on-site photo hazard analysis, and fast drafting of risk assessments, method statements and site reports.
bellmanloop
BellmanLoop is an AI-powered debt collection platform that automates and scales collections with compliance controls, multi-channel and multi-language support, real-time analytics, and SDKs for integration.