What is openvidia AGENTS.md?

Project instructions for OpenVidia, a local proxy that sends requests from different AI clients to NVIDIA NIM using a shared pool of API keys. They describe its mission, architecture, and main modules.

Use them when working on OpenVidia's proxy, desktop dashboard, API compatibility shims, key rotation, cooldowns, request limits, or automatic context reduction.

They give developers the project context needed to change or operate the proxy without misunderstanding how clients, key rotation, limits, and compatibility layers fit together.

How autcir/openvidia configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to autcir/openvidia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/autcir/openvidia/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/autcir/openvidia

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/autcir/openvidia/agents-md/github.svg)](https://agentmods.dev/instructions/autcir/openvidia/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/autcir/openvidia/agents-md"><img src="https://agentmods.dev/badge/instructions/autcir/openvidia/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/autcir/openvidia/agents-md"><img src="https://agentmods.dev/badge/instructions/autcir/openvidia/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,032 This file is loaded in full into every session.

When invoked 1,032 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01032	$0.01032
Opus 5.5	$0.00413	$0.00413
Sonnet 5.5	$0.00206	$0.00206
Haiku 4.5	$0.00103	$0.00103

Measured 12d ago against content hash f2d824208576, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openvidia AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenVidia — Multi-key proxy for NVIDIA NIM

Mission

Multi-key proxy for NVIDIA NIM with a native desktop dashboard. A pool of free-tier API keys behind a single endpoint, with automatic rotation, per-key cooldown, sliding-window RPM limiting, and auto-compaction.

Architecture

Client CLI → localhost:1919/v1 → Proxy Engine → integrate.api.nvidia.com/v1
                                    │
                                    ├─ /v1/chat/completions  (catch-all: opencode, Grok, any OpenAI client)
                                    ├─ /v1/responses         (shim: Codex CLI)
                                    ├─ /v1/messages          (shim: Claude Code)
                                    └─ /v1/models            (upstream model list)

Core modules

File	Lines	Role
`proxy_app.py`	~573	FastAPI app factory, routing, health check, pre-warm
`proxy_state.py`	~730	Thread-safe state: KeyState, cooldown, RPM tracker, circuit breaker
`responses_shim.py`	~1126	Shim `/v1/responses` → `/v1/chat/completions` (Codex CLI)
`anthropic_shim.py`	~705	Shim `/v1/messages` → `/v1/chat/completions` (Claude Code)
`compaction.py`	~784	Context auto-compaction on context overflow
`config.py`	~351	Cross-platform config paths, timeouts, model options
`__main__.py`	~727	Entry point, CLI setup (opencode/codex/grok), tray, server manager
`webui.py`	~472	Web dashboard (pywebview), API endpoints
`server_manager.py`	107	uvicorn start/stop, dual-stack binding
`safe_file.py`	197	Atomic backup of config files
`_upstream_utils.py`	43	Global semaphore + ResourceExhausted detection

Shared key rotation

_rotation_phase() in responses_shim.py is the function shared by all paths:

max 5 attempts per phase, 3 phases with a 1s pause
saturation gate: if <5% of keys are live, fast-fail with 503
probe timeout (90s) on the first attempt for fast dead-model detection
send timeout (180s) on subsequent attempts
handles 429 ResourceExhausted (transient, key untouched) vs 429 rate-limit (cooldown)
imported by proxy_app.py (catch-all), anthropic_shim.py (Claude Code)

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago Changed · +9 lines · +54 tokens per session f2d824208576
2mo ago First seen · 88 lines · 978 tokens per session scan A e8a23aa058f6

Subscribe to this mod's changes

openvidia AGENTS.md is an instructions file published in the GitHub repository autcir/openvidia (8 stars, last pushed 13d ago), licensed MIT. It adds 1,032 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Python anthropic api-gateway fastapi load-balancing nvidia-nim

openvidia AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openvidia AGENTS.mdautcir/openvidia	Instructions file	8	13d ago	MIT	A	1,032	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

openvidia: Instructions file for Codex