BLA
BLA (Blind LLM Agents) is the open-source Blue Defense MCP and CLI built to protect software artifacts against automated AI reverse-engineering workflows.
Ambit is a self-hosted gateway that decides who may use which AI models and work apps, sets spending limits, keeps an audit record, and removes access when someone leaves.
SecurityGo · ShellGitHub @craftsman-appsOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
The AI access layer for enterprises: a self-hosted LLM and MCP gateway on Kubernetes, built on agentgateway and ToolHive.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Ambit is the AI access layer for enterprises. Ambit is a self-hosted gateway, built on agentgateway, ToolHive and other open-source projects, that controls a company's use of AI. It decides who may use which AI models and which work apps (through MCP), sets spending limits, keeps an audit record, and removes access when someone leaves the company. agentgateway handles the traffic and ToolHive runs the MCP servers. Ambit adds identity-provider access rules, a console, per-person app sign-in, budgets, audit and offboarding, in one Helm chart. [README 설치·사용 부분 발췌] Quick startRead the full README ↗
Ambit is a self-hosted gateway, built on agentgateway, ToolHive and other open-source projects, that controls a company's use of AI. It decides who may use which AI models and which work apps (through MCP), sets spending limits, keeps an audit record, and removes access when someone leaves the company.
agentgateway handles the traffic and ToolHive runs the MCP servers. Ambit adds identity-provider access rules, a console, per-person app sign-in, budgets, audit and offboarding, in one Helm chart.
| Without Ambit | With Ambit |
|---|---|
| Each team shares one provider API key, copied into scripts and laptops. | People sign in, or use a personal API key. Provider keys stay inside Ambit. |
| Anyone who has the key can use any model. | Access rules based on your identity provider's groups decide which models and MCP servers each team may use. |
| AI agents connect to work apps on their own, often through one shared service account. | Every MCP call passes one gateway. People connect their own app accounts, tools are checked, and personal data in results is masked. |
| The cost shows up on next month's bill. | Daily limits per group and per person, in requests or in dollars. |
| Nobody can say who sent what to which model. | Every call is recorded, refusals included. Model refusals do not yet show who made them (an agentgateway bug; see Known limitations). |
| Someone leaves, and their keys work until someone remembers to rotate them. | The identity provider disables them, and their keys, sessions and app sign-ins stop at once. |
Blue is the path every request takes; grey is how admins and your identity provider set things up.
Every call is kept in an audit log, refusals included, and shown in the console. Model refusals do not yet show who made them (an agentgateway bug; see Known limitations).
On a laptop with Docker (macOS, Linux, or Windows with WSL 2):
brew install craftsman-apps/tap/ambit # or: curl -fsSL https://ambitproject.dev/install.sh | sh
ambit local up
ambit local up creates a local kind cluster, installs Ambit for testing only (plain HTTP, one gateway replica), adds a model and an access rule, makes a first call, and prints the console address and the sign-in.
The full guide has the other install methods (PowerShell, npm, go install) and the next steps.
Ambit is pre-1.0. The API is ambitproject.dev/v1alpha1 and can change between releases.
| Tested | Not tested yet |
|---|---|
| Install and all features on kind, in CI on every pull request | Azure OpenAI, Amazon Bedrock and Vertex AI with real cloud accounts |
| Company sign-in through a test Keycloak, external ClickHouse and Valkey, GitOps with Argo CD | A 24-hour soak test (CI runs a 5-minute soak) |
v1alpha1.Ambit is built on these projects. Each keeps its own licence.
| Project | Use in Ambit | Licence |
|---|---|---|
| agentgateway | LLM and MCP traffic | Apache-2.0 |
| ToolHive | Runs MCP servers | Apache-2.0 |
| Dex | Sign-in and tokens | Apache-2.0 |
| Gateway API | Routing objects | Apache-2.0 |
| ClickHouse | Audit storage | Apache-2.0 |
| OpenTelemetry Collector | Audit pipeline | Apache-2.0 |
| Valkey | Budget counters | BSD-3-Clause |
| envoyproxy/ratelimit | Budget enforcement | Apache-2.0 |
| MCP Go SDK | Preset checks and test MCP servers | Apache-2.0 (older code MIT) |
| Kubernetes client libraries, controller-runtime, CEL-go | Controller and rules | Apache-2.0 |
| React, TanStack, Tailwind CSS, Radix UI | Console front end | MIT |
| IBM Plex (Fontsource) | Console fonts | SIL OFL 1.1 |