Try Bifrost Enterprise free for 14 days.
Request access
[ CLI CODING AGENTS + BIFROST ]

Enterprise Controls for
All CLI Coding Agents

One gateway between your favourite coding agents and LLM providers. Set budgets, enforce policies, and monitor every request without changing agent workflows.

[ SUPPORTED CLI AGENTS ]

Four Powerful Coding Agents, One Unified Gateway

Each CLI agent brings unique capabilities. Bifrost provides the enterprise controls, multi-provider access, and observability that all of them need at scale.

Claude Code logo

Claude Code

Official CLI Agent for Anthropic Models

Provider: Anthropic

    Codex CLI logo

    Codex CLI

    OpenAI's powerful code generation CLI

    Provider: OpenAI

      Gemini CLI logo

      Gemini CLI

      Google Gemini powered coding agent

      Provider: Google

        OpenCode logo

        OpenCode

        Open source coding agent framework

        Provider: Multi-provider

          [ CORE CAPABILITIES ]

          What Bifrost Adds to Every CLI Agent

          Whether you use Claude Code, Codex CLI, Gemini CLI, or OpenCode, routing through Bifrost gives you enterprise-grade controls without changing developer workflows.

          Multi-provider model access

          Every CLI agent gets access to 1000+ models through Bifrost. Switch between Anthropic, OpenAI, Google, AWS Bedrock, and more without reconfiguring your agent.

          1000+ models

          Enterprise security & governance

          All agent requests route through Bifrost, applying guardrails, PII redaction, content policies, and role-based access controls transparently.

          SOC 2 Type II ready

          Unified cost tracking

          Track LLM spend across all CLI agents from a single dashboard. Virtual keys enforce per-team budgets. Export via the logs API or OTEL for custom cost analysis.

          Per-request costs

          Centralized observability

          Every request from Claude Code, Codex CLI, Gemini CLI, and OpenCode is logged with full metadata. Export to any observability stack via OpenTelemetry.

          OTEL native

          Automatic failover & load balancing

          When a provider hits rate limits or experiences an outage, Bifrost automatically routes agent requests to healthy providers. Adaptive load balancing keeps throughput stable.

          99.999% uptime

          Semantic caching

          Repeat or near-identical queries across agents resolve instantly from cache, cutting costs and reducing latency for common coding operations.

          Cost savings

          [ SETUP ]

          Three Steps to Unified CLI Agent Governance

          Deploy Bifrost once, configure your agents, and get instant enterprise controls across all CLI coding tools.

          STEP 01

          Deploy Bifrost Gateway

          Run Bifrost as a standalone service in your VPC or use managed hosting. Configure your LLM providers and optional guardrails through the dashboard.

          # pull and start bifrost
docker pull bifrost-gateway
docker run -p 8080:8080 bifrost
          STEP 02

          Point your CLI agent at Bifrost

          Set the API base URL environment variable for your chosen agent. Each agent has slightly different configuration requirements.

          # Claude Code
export ANTHROPIC_BASE_URL="http://localhost:8080"

# Codex CLI (must end in /v1)
export OPENAI_API_BASE="http://localhost:8080/openai/v1"

# Gemini CLI
export GEMINI_API_BASE="http://localhost:8080"

# OpenCode
export API_BASE_URL="http://localhost:8080"
          STEP 03

          Start coding with enterprise controls

          Launch your agent and start coding. All requests automatically route through Bifrost with full observability, cost tracking, and guardrails applied.

          # Use Bifrost CLI for guided setup
npx -y @maximhq/bifrost-cli

# Or launch agents directly
claude code
codex generate
gemini chat
opencode

          [ AGENT CONFIGURATION ]

          Configuration for Each CLI Agent

          Each agent requires slightly different configuration. Here are the specifics for connecting to Bifrost.

          Claude Code logo

          Claude Code

          Environment Variable:

          ANTHROPIC_BASE_URL

          Value:

          http://localhost:8080

          Supports MCP tool injection via Bifrost

          Example command:

          claude mcp add --transport http bifrost http://localhost:8080/mcp
          Codex CLI logo

          Codex CLI

          Environment Variable:

          OPENAI_API_BASE

          Value:

          http://localhost:8080/openai/v1

          Must end in /v1 to avoid 404 errors

          Example command:

          codex config set api-base http://localhost:8080/openai/v1
          Gemini CLI logo

          Gemini CLI

          Environment Variable:

          GEMINI_API_BASE

          Value:

          http://localhost:8080

          Standard Google AI endpoint format

          Example command:

          gemini config set base-url http://localhost:8080
          OpenCode logo

          OpenCode

          Environment Variable:

          API_BASE_URL

          Value:

          http://localhost:8080

          Flexible multi-provider configuration

          Example command:

          opencode config base http://localhost:8080

          [ BIFROST CLI ]

          One Command to Launch Any Coding Agent

          Bifrost CLI is an interactive terminal tool that launches coding agents through a Bifrost gateway without manual configuration. Run a single command, select your preferred agent and model through a guided setup, and start coding with enterprise controls.

          npx -y @maximhq/bifrost-cli

          [ COMPARISON ]

          Standalone CLI Agents vs. CLI Agents + Bifrost

          FeatureStandalone AgentsAgents + Bifrost
          Multi-provider accessNo20+ providers
          Automatic failoverNoAcross all providers
          Cost trackingNoReal-time per request
          Team budgetsNoVirtual keys + limits
          Security guardrailsNoPII redaction + policies
          Request observabilityNoFull logs + OTEL export
          Semantic cachingNoReduce costs + latency
          MCP tool integrationClaude Code onlyAll agents via gateway

          [ USE CASES ]

          Real-World Scenarios for Multi-Agent Workflows

          Multi-agent development workflows

          Teams use different CLI agents for different tasks: Claude Code for architecture, Codex for quick scripts, Gemini for code review, OpenCode for deployments. Bifrost provides unified governance.

          Model performance comparison

          Run the same coding task through Claude Code, Codex CLI, and Gemini CLI to compare quality, speed, and cost. Bifrost logs performance metrics for each provider.

          Enterprise security compliance

          Organizations route all CLI agent traffic through Bifrost to enforce PII redaction, content policies, and audit trails for SOC 2 Type II, HIPAA, and GDPR compliance.

          Department-level cost management

          Platform teams set budgets for each engineering department. Real-time dashboards show which teams, projects, and agents are driving LLM spend.

          High-availability production coding

          When Anthropic hits rate limits, Claude Code requests automatically route to Bedrock. When OpenAI hits rate limits or errors, Codex CLI switches to Azure OpenAI.

          Centralized AI governance

          Security teams enforce organization-wide policies across all CLI agents from a single control plane. No need to configure guardrails per agent.

          [ ENTERPRISE FEATURES ]

          Production-Ready Governance for All Agents

          Bifrost provides the enterprise controls platform teams need before rolling out CLI agents organization-wide.

          Virtual keys per team

          Create separate credentials for each team with independent rate limits and budgets.

          Content filtering

          Detect and redact PII, sensitive data, and API keys before requests reach models.

          Audit trails

          Complete tamper-evident logs of every request for compliance and security.

          SSO integration

          Authenticate via Google, GitHub, Okta, or any SAML/OIDC provider.

          Adaptive routing

          Traffic distributes intelligently based on real-time health and performance.

          In-VPC deployment

          Deploy entirely within your network perimeter for maximum security.

          Ready to Unify Your CLI Agent Infrastructure?

          Deploy Bifrost once and get enterprise controls, multi-provider access, and unified observability across Claude Code, Codex CLI, Gemini CLI, and OpenCode.

          [ BIFROST FEATURES ]

          Open Source & Enterprise

          Everything you need to run AI in production, from free open source to enterprise-grade features.

          01 Governance

          SAML support for SSO and Role-based access control and policy enforcement for team collaboration.

          02 Adaptive Load Balancing

          Automatically optimizes traffic distribution across provider keys and models based on real-time performance metrics.

          03 Cluster Mode

          High availability deployment with automatic failover and load balancing. Peer-to-peer clustering where every instance is equal.

          04 Alerts

          Real-time notifications for budget limits, failures, and performance issues on Email, Slack, PagerDuty, Teams, Webhook and more.

          05 Log Exports

          Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export capabilities for compliance, monitoring, and analytics.

          06 Audit Logs

          Comprehensive logging and audit trails for compliance and debugging.

          07 Vault Support

          Secure API key management with HashiCorp Vault, AWS Secrets Manager, Google Secret Manager, and Azure Key Vault integration.

          08 VPC Deployment

          Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls.

          09 Guardrails

          Automatically detect and block unsafe model outputs with real-time policy enforcement and content moderation across all agents.

          [ SHIP RELIABLE AI ]

          Try Bifrost Enterprise with a 14-day Free Trial

          [quick setup]

          Drop-in replacement for any AI SDK

          Change just one line of code. Works with OpenAI, Anthropic, Vercel AI SDK, LangChain, and more.

          1import os
          2from anthropic import Anthropic
          3
          4anthropic = Anthropic(
          5 api_key=os.environ.get("ANTHROPIC_API_KEY"),
          6 base_url="https://<bifrost_url>/anthropic",
          7)
          8
          9message = anthropic.messages.create(
          10 model="claude-3-5-sonnet-20241022",
          11 max_tokens=1024,
          12 messages=[
          13 {"role": "user", "content": "Hello, Claude"}
          14 ]
          15)
          Drop in once, run everywhere.

          [ FREQUENTLY ASKED QUESTIONS ]

          Common Questions

          Can I use multiple CLI agents with the same Bifrost gateway?

          Yes. Bifrost provides 100% compatible endpoints for OpenAI, Anthropic, and Gemini APIs, allowing you to route Claude Code, Codex CLI, Gemini CLI, and OpenCode through the same gateway simultaneously. Each agent gets access to all configured providers. Read more about Bifrost CLI.

          How do I switch models or providers for a specific CLI agent?

          You can configure model routing through Bifrost virtual keys, which specify which models each key can access. Alternatively, use Bifrost CLI (npx @maximhq/bifrost-cli) for guided setup that lets you select models before launching agents. The gateway handles provider routing automatically.

          Does routing CLI agents through Bifrost add latency?

          Bifrost adds approximately 11µs of gateway overhead per request at 5,000 RPS. This is effectively invisible compared to LLM response times that typically range from hundreds of milliseconds to several seconds. Read more about Bifrost becnhmarks.

          Can I use MCP tools with all CLI agents through Bifrost?

          Claude Code has native MCP support that integrates directly with Bifrost MCP endpoints. Other agents can access MCP-connected tools through Bifrost's gateway, though the integration may vary by agent. The Bifrost CLI automatically registers MCP servers for Claude Code.

          How are costs tracked across different CLI agents?

          Bifrost logs every request with model, provider, token counts, and cost. Use virtual keys to tag requests by agent, team, or environment. Export via the logs API or OTEL to build cost breakdowns in your BI tool of choice.

          What happens if one provider goes down while using CLI agents?

          Bifrost automatically fails over to healthy providers. If Claude Code is configured to use Anthropic but hits rate limits, requests transparently route to AWS Bedrock or Google Vertex AI. Developers experience zero downtime.