Adapters

Adapter Integration

FORG adapters connect your editor, AI coding assistant, CLI, or internal agent to the local FORG agent. Each adapter hooks into the tool's native extension or hook system, emits structured signals after every AI interaction, and receives real-time policy decisions back from the rule engine — without capturing any prompt or completion text.

What is an adapter?

An adapter is the integration layer between an AI coding tool and the FORG agent. It hooks into adapter-specific integration points — hooks files, MCP settings, workspace tasks, Lua autocommands, or system prompt injections — and communicates session events (tool calls, session boundaries, token counts) to the forg binary over 127.0.0.1:6247.

Adapters operate on the same open protocol: a JSON POST to the local agent, signed with an HMAC session key, followed by a synchronous policy response. If the agent is not running, adapters fail open so your workflow is never interrupted.

Claude CodeOfficial

Session lifecycle, tool calls, token budgets, and cost attribution for Claude Code.

CursorOfficial

Track Cursor chat, Composer, Cmd-K, project attribution, and model usage.

VS CodeOfficial

VS Code extension telemetry for AI extensions, editor activity, and session signals.

WindsurfOfficial

Cascade session observability, chat metadata, and multi-step flow tracking.

JetBrains IDEsOfficial

One adapter for IntelliJ, PyCharm, WebStorm, GoLand, Rider, DataGrip, and CLion.

OpenCodeOfficial

Native hook integration for OpenCode sessions, tasks, and tool usage.

NeovimOfficial

Lua plugin telemetry for AI-assisted terminal-native workflows.

GitHub CopilotOfficial

Copilot completions, Copilot Chat, seat utilization, and ROI measurement.

ContinueOfficial

Open-source AI coding assistant telemetry across VS Code and JetBrains.

OpenAI Codex CLIOfficial

MCP server registration in ~/.codex/config.yaml for Codex CLI session telemetry.

Gemini CLIOfficial

MCP server registration in ~/.gemini/settings.json for Gemini CLI session tracking.

AiderOfficial

Pair-programming session telemetry for Aider workflows via AGENTS.md injection.

ZedOfficial

MCP server registration in Zed settings for AI workflow telemetry.

Warp TerminalOfficial

MCP server registration in ~/.warp/mcp_config.json for Warp terminal AI sessions.

PowerShellOfficial

PowerShell profile injection to expose forg-mcp as a shell function.

Amazon Q DeveloperPlanned

Amazon Q usage visibility for AWS-heavy engineering teams.

Sourcegraph CodyPlanned

Cody chat and code intelligence session metadata.

TabninePlanned

Tabnine usage telemetry for completion-heavy teams.

SupermavenPlanned

Supermaven completion metadata and developer workflow attribution.

Replit Agent / GhostwriterProtocol-compatible

Emit FORG signals from Replit-based AI build sessions.

DevinProtocol-compatible

Protocol path for autonomous software-engineering agent telemetry.

Augment CodePlanned

Augment Code usage telemetry for enterprise codebase assistants.

Qodo / CodiumAIPlanned

Testing and code-quality assistant telemetry.

CodeRabbitProtocol-compatible

Pull-request AI review events through protocol integration.

Bolt.newProtocol-compatible

Browser-based build-agent sessions through protocol events.

LovableProtocol-compatible

App-builder AI workflow telemetry through the open protocol.

v0 / Vercel AI toolsProtocol-compatible

Design/build generation telemetry for v0-style workflows.

Roo CodeOfficial

MCP server registration in ~/.roo/mcp_settings.json for Roo Code agent workflows.

ClineOfficial

MCP server registration for Cline agentic VS Code sessions, tool calls, and model usage.

GoosePlanned

Local agent session telemetry for Goose workflows.

CrewAIProtocol-compatible

Multi-agent workflow telemetry through custom protocol events.

LangGraph agentsProtocol-compatible

Graph-based agent run metadata and outcome tracking.

AutoGen agentsProtocol-compatible

Agent conversation metadata for AutoGen workflows.

Custom internal agentsProtocol-compatible

Internal AI agents can emit FORG signals with a signed HTTP POST.

Shell scripts / CI agentsProtocol-compatible

Emit AI-job telemetry from scripts, CI pipelines, and automation.

Build Your OwnProtocol-compatible

Open protocol documentation. Any tool that can make HTTP requests can be a FORG adapter.

Claude Code

The Claude Code adapter installs FORG-managed hooks into ~/.claude/settings.json so session boundaries, tool calls, and token metadata emit directly through forg emit.

It is the lowest-latency path in the catalog because Claude Code calls FORG from native hook events instead of going through MCP.

forg connect claude-code

Cursor

Cursor uses native MCP registration, so FORG shows up alongside your other MCP servers with no project-level rules files to maintain.

Once connected, Cursor sessions, tool activity, and model usage flow into the same FORG timeline as every other supported editor.

forg connect cursor

VS Code

The VS Code adapter registers forg-mcp in VS Code's MCP settings so AI sessions can be attributed without adding an extension-specific FORG plugin.

It works well for mixed environments where the same team uses Copilot, Continue, Cline, and internal MCP-aware workflows inside VS Code.

forg connect vscode

Windsurf

Windsurf connects through MCP and gives FORG visibility into Cascade sessions, tool use, and model-level cost allocation.

Use it when you want the same governance surface across Windsurf and the rest of your AI coding stack.

forg connect windsurf

JetBrains

JetBrains IDEs connect through an MCP configuration path that works across IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, and the rest of the IntelliJ family.

FORG keeps the install idempotent so teams can standardize the same connection flow across multiple IDEs on one machine.

forg connect jetbrains

OpenCode

The OpenCode adapter uses OpenCode's native MCP config so session lifecycle, task tracking, and tool-use metadata appear in FORG automatically.

It's the fastest way to bring terminal-native OpenCode sessions under the same budgets and rule triggers as your editors.

forg connect opencode

Neovim

Neovim uses a Lua plugin file generated by FORG, giving you terminal-native session telemetry without wrapping your editor startup command.

The adapter is especially useful when teams mix Neovim with MCP-based tools and still want one dashboard and one budget surface.

forg connect neovim

GitHub Copilot

The Copilot adapter uses MCP so Copilot-enabled workflows can report session metadata, model usage, and cost allocation into FORG with the same one-command install flow.

That makes Copilot seat usage visible next to Claude Code, Cursor, and every other officially supported adapter.

forg connect copilot

Continue

Continue also connects through MCP, which makes it easy to track provider-agnostic sessions even when teams swap between Anthropic, OpenAI, Gemini, or local models.

FORG keeps the attribution and budget layer consistent regardless of which underlying model Continue routes to.

forg connect continue

OpenAI Codex CLI

The Codex adapter writes a FORG MCP server entry into ~/.codex/config.yaml so Codex CLI sessions are visible without custom wrapper scripts.

It is a clean fit for terminal-first teams that want session telemetry, model usage, and cost tracking from Codex alongside Claude Code and Gemini CLI.

forg connect codex

Gemini CLI

Gemini CLI uses MCP registration, giving Google Gemini sessions the same telemetry path, dashboards, and rule enforcement as the rest of the FORG adapter catalog.

It is especially useful for teams comparing Gemini usage against other providers in one shared budget surface.

forg connect gemini-cli

Aider

Aider does not expose native MCP support today, so FORG injects a managed context block into ~/AGENTS.md so pair-programming sessions are still attributed correctly.

For full signal tracking during terminal use, run forg on before launching Aider so your shell session is already under FORG observation.

forg connect aider

Warp Terminal

Warp uses MCP config registration, letting FORG observe Warp's AI-assisted terminal workflows without changing how developers open or use Warp.

That makes Warp a good bridge between shell-native workflows and the rest of your editor-based adapter fleet.

forg connect warp

Cline

Cline connects through MCP so agentic VS Code sessions, tool calls, and session boundaries are visible in FORG immediately after setup.

Teams using Cline for longer-running task execution can keep the same budget enforcement and recording they use everywhere else.

forg connect cline

Roo Code

Roo Code uses the CLI slug roo while the catalog slug remains roo-code, and FORG handles that mismatch for you during connection.

The adapter exposes Roo's model telemetry and tool metadata through MCP so agent workflows in VS Code land in the same FORG timeline as Cline and Continue.

forg connect roo

Zed

Zed registers forg-mcp in its settings so AI-assisted editing sessions can be recorded without custom project files or editor wrappers.

Once connected, Zed activity participates in the same real-time rules, dashboards, and cost reporting as other official adapters.

forg connect zed

PowerShell

The PowerShell adapter injects a managed forg-mcp function into your PowerShell profile so FORG is ready anywhere PowerShell starts.

It is the cleanest path for Windows-heavy teams that want shell-native MCP access without manual profile editing.

forg connect powershell

Adapter slots by plan

Each plan allows a different number of simultaneously active adapters (adapter slots).

PlanActive adapter slots
Solo5$19/mo
ProfessionalUnlimited$39/mo
TeamUnlimited$199/mo base
BusinessUnlimited$599/mo base
EnterpriseUnlimitedCustom

On Solo, you can switch your active adapter at any time via forg connect <name>. Switching deactivates the previously active adapter.

How adapters work

All adapters communicate with the local FORG agent over HTTP on 127.0.0.1:6247. The agent:

  1. Validates the signal with HMAC-SHA256 using a per-session key
  2. Applies any matching rules synchronously (for blocking actions)
  3. Buffers the signal and forwards it to the Rule Engine at forg.pro/engine/v1
  4. Returns a response indicating whether the signal was accepted or blocked

If the local agent is not running, adapters fail open — the AI tool call proceeds normally and the signal is dropped. This ensures FORG never interrupts your workflow.

© 2026 UpgradIQ, Inc.Edit this page on GitHub