Tools MCP ServersHOT Categories Trending New Best Lists Compare Guides

Tools MCP ServersHOT Categories Trending New Best Lists Compare

deltallm

deltallm

Active·★ 20·MIT·Updated 2026-10-22

DeltaLLM is a self-hosted AI gateway providing a single OpenAI-compatible API to over 100 LLM providers. It streamlines LLM integration with built-in enterprise features like routing, cost tracking, and security guardrails.

#AI Gateway#LLM Management#OpenAI API Proxy#Enterprise Controls#API Routing#Security Guardrails#Cost Management

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.

Best by use case About Contact Advertise Privacy Policy Terms of Use QYS GitHub Buy me a coffee ☕

Browse by Category

MCP Servers Code Assistant Workflow Automation RAG / Knowledge Base Multi-Agent Browser Automation LLM Infra Dev Tooling Observability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

#Multi-Provider Integration

$ Install

$ MASTER_KEY=$(python3 -c 'import secrets; print("sk-" + secrets.token_hex(20) + "A1")') && SALT_KEY=$(python3 -c 'import secrets; print(secrets.token_hex(32))') && git clone https://github.com/deltawi/deltallm.git && cd deltallm && cp config.example.yaml config.yaml && echo "DELTALLM_MASTER_KEY=$MASTER_KEY" > .env && echo "DELTALLM_SALT_KEY=$SALT_KEY" >> .env && echo "OPENAI_API_KEY=sk-your-openai-key" >> .env && echo "[email protected]" >> .env && echo "PLATFORM_BOOTSTRAP_ADMIN_PASSWORD=ChangeMe123!" >> .env && docker compose --profile single up -d --build

↗ Visit site ★ GitHub

01

Features

01Unified OpenAI-compatible API for 100+ LLM providers.

02Virtual API Keys with granular controls like budgets, rate limits, and model restrictions.

03Advanced routing and failover strategies with automatic retries.

04Built-in security guardrails including PII detection and prompt injection protection.

05Comprehensive spend tracking with cost attribution per key, team, and model.

02

Compatibility

Python

Runtime

Verified via docs

Docker

Containerization

Verified via docs

Kubernetes

Orchestration

Verified via docs

PostgreSQL

Database

Verified via docs

Redis

Cache/Message Broker

Verified via docs

03

Quick start

1

$ MASTER_KEY=$(python3 -c 'import secrets; print("sk-" + secrets.token_hex(20) + "A1")')

2

$ SALT_KEY=$(python3 -c 'import secrets; print(secrets.token_hex(32))')

3

$ git clone https://github.com/deltawi/deltallm.git

4

$ cd deltallm

5

$ cp config.example.yaml config.yaml

6

$ echo "DELTALLM_MASTER_KEY=$MASTER_KEY" > .env

7

04

Use cases

↳Centralized LLM Access Management: Simplify API key management and developer integration for multiple LLM providers.

↳Cost Control and Optimization: Implement budgets and track spending to optimize LLM usage costs across teams and models.

↳Enhanced Security and Compliance: Apply guardrails for PII detection and prompt injection protection in LLM interactions.

↳Multi-vendor LLM Strategy: Route requests across various LLM providers based on performance, cost, or availability to avoid vendor lock-in.

05

Alternatives

⚡Top VS:

VSbifrost★9.0k→VSllmkit★15→VStunnel-client★589→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page

01Features 02Compatibility 03Quick start 04Use cases 05Alternatives

$ echo "DELTALLM_SALT_KEY=$SALT_KEY" >> .env

8

$ echo "OPENAI_API_KEY=sk-your-openai-key" >> .env

9

$ echo "[email protected]" >> .env

10

$ echo "PLATFORM_BOOTSTRAP_ADMIN_PASSWORD=ChangeMe123!" >> .env

11

$ docker compose --profile single up -d --build

emisar

★331

→

bifrost★ 9.0k

Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

tunnel-client★ 589

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

An MCP that lets AI tools securely connect to your infrastructure, write IaaS code, debug issues, and assist during incidents - without risking production stability. Built for security teams to approve and infrastructure teams to experience like magic.

agent-harness-generator★ 713

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

Local MCP gateway that cuts your agent's tool-token overhead ~90%. Every MCP server's tools collapse to 3 meta-tools the agent searches on demand. Measured: 97% less per request, same results. Keys in your OS keychain, no cloud.

Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift).

See all alternatives →

deltawi /

deltallm

↗

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface

20MIT

Last commit1d ago

StatusActive

CategoryLLM Infra

Links

Documentation↗Discussion↗Issues↗Releases↗

Cloud Infrastructure

Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit