Now in private beta — Join the waitlist
Agentic AI platform for developers

Build and run with
AI agents that ship code.

Forge is an agentic platform where AI agents plan, code, test, and open real GitHub pull requests from your tickets — with per-step cost estimates before anything runs. You approve the plan, review the PR, and merge. Alternative to Cursor, Copilot, and Devin.

Start for free Watch the demo

Five agents. One pipeline.
You choose which run.

Every mission flows through a configurable pipeline of specialized agents. Enable or disable any step — skip docs, skip testing, or run the full suite.

🧠
Planning Atlas-7
</>
Coding Helix-1
🧪
Testing Nova-3
🔍
Review Echo-5
📄
Docs Prism-2

Click any step to enable / disable it

Planning

Breaks the task into sub-steps, identifies files, and builds the execution plan.

Coding

Implements the plan — writes code, creates files, and iterates until the build passes.

Testing

Writes and runs tests. Fixes failures automatically before handing off.

Review

Code review, linting, CI checks. Pushes fixes and opens the PR when ready.

Docs

Generates or updates documentation, changelogs, and inline comments.

Configure every mission before it starts.

The New Mission modal lets you set type, priority, labels, repo, budget cap — and toggle each pipeline step on or off before launch.

Know the cost per step, before you start.

Forge estimates costs for each agent role upfront — broken down by pipeline step. Track spend in real time and set budget caps to stay in control.

Per-Step Estimates

See cost per agent role before approving. Know exactly where your budget goes — planning, coding, testing, review, or docs.

👁

Real-Time Tracking

Watch costs accumulate token by token. Every API call is logged with its exact price per agent.

🛡

Budget Caps

Set monthly budgets and per-mission limits. Agents pause automatically when thresholds are hit.

📊

History-Calibrated

Estimates improve over time. Forge uses your historical data to predict costs by complexity tier.

Cost Estimate $1.93 – $3.90
Atlas-7
6% $0.185
Helix-1
79% $2.300
Prism-2
4% $0.130
Echo-5
4% $0.125
Nova-3
6% $0.180
Budget Settings Pro Plan
Monthly Budget
$150.00
This Month Spend
$20.34
Alert Threshold
64%
Budget Usage 13.6%
Forecast: Based on your average daily spending of $0.75, you'll spend approximately $23.35 by month-end (16% of budget).

Model Pricing — You Only Pay What You Use

Bring your own API keys. Forge adds zero markup on model costs.

Gemini 3 Flash $0.50/M in $3.00/M out Quick tasks, testing
Gemini 3.1 Pro $2.00/M in $12.00/M out Planning, architecture
Claude Sonnet 4.6 $3.00/M in $15.00/M out Balanced coding
Claude Opus 4.6 $15.00/M in $75.00/M out Complex coding, reasoning
Gemini 2.5 Flash $0.30/M in $2.50/M out High-volume, cost-efficient

One platform. Every surface.

Web dashboard, CLI, and mobile app — all connected to the same agent pipeline.

🖥

Web Dashboard

Full-featured GUI with real-time agent traces, kanban boards, CI integration, and the Intelligence Hub for model management and cost tracking.

⌨️

CLI for Developers

Everything the GUI does, from your terminal. Create missions, approve plans, watch agent traces, and manage budgets — without leaving your editor.

📱

Mobile App

Review and approve from anywhere. Resume tasks, check costs, and manage your agents on the go — all from your phone.

Developer-first

Your terminal is your cockpit

The Forge CLI gives you full parity with the web dashboard. Create missions, stream agent output, approve plans, and track spend — all from the command line.

  • > Create and manage missions
  • > Stream real-time agent traces
  • > Approve or reject plans inline
  • > Check budget and cost per mission
  • > Manage API keys and agent pipeline
Terminal
$forge mission create "Add rate limiting to API"
Created mission msn_0xA3F1 on main
Pipeline: Atlas-7 -> Helix-1 -> Nova-3 -> Echo-5
Estimated cost: $1.93 – $3.90
$forge mission approve msn_0xA3F1
Plan approved. Helix-1 is now implementing...
$forge usage
This month: $20.34 / $150.00 budget
Active missions: 3
Budget remaining: $129.66
FORGE-INSTANT
Missions
ALL RUNNING APPROVAL
WORKING $0.042
Refactor auth middleware for high-concurrency websocket...
msn_0x9FA2 main 2h ago
AWAITING APPROVAL $0.128
Implement zero-knowledge proof verification for transaction privacy...
msn_0x7B41 feature/zkp-core 5h ago
COMPLETED $0.009
Optimize vector DB indexing for sub-10ms query latency
msn_0x2C18 infra/vdb-opt 1d ago
FAILED $0.000
Automated stress testing of the Ethereum mainnet bridge node
msn_0x1E94 test/load-bridge 2d ago
MISSIONS ACTIVITY PROJECTS USAGE PROFILE
Coming soon

Manage agents from your pocket

The Forge mobile app lets you stay connected to your agents wherever you are. Get push notifications when a plan needs approval, review diffs, check costs, and resume paused tasks — all from your phone.

  • > Push notifications for approvals and failures
  • > Review and approve plans on the go
  • > Real-time cost tracking per mission
  • > Resume or cancel tasks remotely
  • > Full mission history and agent traces

Watch Forge ship a feature.

From ticket to merged PR in under 5 minutes — fully autonomous.

Everything your team needs.
Nothing you don't.

Forge is a complete AI engineering platform — not just a code autocomplete. Every feature is designed for real production workflows.

🧠

Autonomous Agent Loop

Plan, code, test, fix — fully automated. Self-healing agents iterate until CI passes.

plan > execute > review self-healing
🔀

Auto PR Creation

Branches pushed, PRs opened with full descriptions, merge gates enforced — zero manual steps.

auto-push PR description merge gates

CI/CD Integration

Real-time GitHub Actions monitoring. Agents wait for CI, fix failures, and re-push automatically.

GitHub Actions real-time checks CI gate
🔔

Notifications

Get notified when agents need input or finish work — via Slack, email, or webhooks.

Slack email webhooks
🎯

Goals & Projects

Set OKRs, auto-generate missions from goals, and track progress across repositories.

OKRs AI planning batch creation
💰

Intelligence Hub

Full cost analytics, model comparison, usage audit logs, and budget forecasting.

audit log budget caps model analytics
🤖

Multi-Model Support

Use Claude, Gemini, or local models via Ollama. Assign different models to different agent roles.

Claude Gemini Ollama
🛡️

Auth & Access Control

GitHub OAuth, API tokens, role-based access. Every action scoped to your organization.

GitHub OAuth API tokens org scoping
📡

Real-Time Traces

Watch agents think and work in real time. Live diffs, tool calls, and reasoning — via WebSocket.

WebSocket live diff agent chat

Frequently asked questions

What is Forge and how does it work?

Forge is an agentic AI platform where AI agents autonomously turn your tickets into merged pull requests. You describe work in plain language, and Forge's agent pipeline reads your codebase, proposes a step-by-step plan with per-agent cost estimates, and — after your approval — implements the code in an isolated git worktree, runs tests, opens a GitHub pull request, and waits for CI to pass. Build and run with AI agents — you review and merge.

How is Forge different from Cursor, GitHub Copilot, or Devin?

Cursor and GitHub Copilot are code assistants — they help you write code in your editor, but you still handle planning, testing, CI, and pull request creation. Devin is a fully autonomous agent but offers limited cost transparency. Forge is fully autonomous (ticket to merged PR) with mandatory human approval gates, per-step cost breakdowns before execution, a configurable 5-agent pipeline, and budget caps. You bring your own API keys with zero markup on model costs.

How much does it cost to run a mission?

Most tickets cost $0.08–$1.20 in LLM API costs. Complex features with 20+ steps typically cost $2–5. Forge shows you the per-agent cost breakdown (Planning, Coding, Testing, Review, Docs) before anything runs, so there are never surprises. You bring your own API keys and Forge adds zero markup.

What AI models does Forge support?

Forge supports Claude (Sonnet 4.6, Opus 4.6), Google Gemini (3 Flash, 3.1 Pro, 2.5 Flash), and local models via Ollama. You can assign different models to different pipeline roles — for example, Gemini Flash for planning (cheaper) and Claude Sonnet for coding (better quality). Models are swappable per mission or per agent role.

Is it safe to use on production codebases?

Yes. Every mission runs in an isolated git worktree — the agent never touches your main branch directly. Nothing is pushed without human approval. The output is a standard GitHub PR that goes through your normal code review and CI pipeline. Role-based access control (Viewer, Engineer, Admin) ensures only authorized users can approve and merge.

What is the agent pipeline?

Forge uses a configurable 5-agent pipeline: Planning (Atlas-7) reads your codebase and creates an execution plan, Coding (Helix-1) implements the plan, Testing (Nova-3) writes and runs tests, Review (Echo-5) performs code review and opens the PR, and Documentation (Prism-2) generates docs. Each step can be toggled on or off per mission, and the cost estimate updates in real-time as you configure it.

Can I use Forge from the terminal?

Yes. The Forge CLI has full feature parity with the web dashboard. You can create missions, stream real-time agent traces, approve plans, check budget usage, and manage your pipeline — all without leaving your terminal. A mobile app is also coming soon for approvals on the go.

Ready to ship
10x faster?

Join engineering teams already using Forge to clear their backlogs and ship production-quality code autonomously.

Free to try. No credit card required. Cancel anytime.