ModelReins – The Browser for AI Tools
Article URL: https://modelreins.com Comments URL: https://news.ycombinator.com/item?id=47635601 Points: 3 # Comments: 1
Stop juggling AI tools.Start orchestrating them.
Route tasks to the right model at the right cost. Claude, Codex, Ollama, or any AI tool. Direct API keys, no subscriptions required, no lock-in.
One dashboard, any provider.
+N
Scale on your terms. No artificial limits. Self-hosted: unlimited workers on your own hardware. SaaS: plans that grow with you. Every machine you own is a potential worker node.
Worker ↔ AI Providers
dashboard never sees your keys
Zero-knowledge. Your keys stay yours. Workers talk directly to providers using your API keys — not subscriptions that can be revoked. Prompts, code, responses never pass through our servers. We orchestrate. We don't eavesdrop. And we don't lock you in.
Before
18%
After
94%
No vendor lock-in. Ever. Vendors change terms overnight. Subscriptions get restricted. APIs get throttled. ModelReins workers use direct API keys — no subscriptions required, no vendor lock-in, no surprises.
Opus
rate limited
↓ auto-failover
Sonnet
routed
Rate limited? Work never stops. Hit a limit on Opus — the router instantly fails over to Sonnet. Sonnet full? Ollama picks it up locally for free. Zero downtime. Zero babysitting.
Live Signal Feed
What it looks like
One command. Your AI workforce is online.
worker — haiku-carbug
$ npx modelreins-worker
| / | ___ __| | ___| | _ \ _() __ ___ | |/| |/ _ \ / _
|/ _ \ | |_) / _ \ | '_ \/ __| | | | | (_) | (_| | __/ | _ < __/ | | | \__ \ |_| |_|\___/ \__,_|\___|_|_| \_\___|_|_| |_|___/ by MEDiAGATO__ |/ _ \ | |_) / _ \ | '_ \/ __| | | | | (_) | (_| | __/ | _ < __/ | | | \__ \ |_| |_|\___/ \__,_|\___|_|_| \_\___|_|_| |_|___/ by MEDiAGATO__Worker: haiku-carbug Provider: anthropic (haiku-4.5) Server: app.modelreins.com Tags: draft,triage,cheap,fast Session: spawn
[20:24:01] Ready — waiting for jobs... [20:24:17] >>> Job #803 claimed [20:24:17] Prompt: Write a product description for ModelReins... [20:24:17] Spawning: anthropic-cli "Write a product description..." [20:24:22] <<< Job #803 complete (exit 0, 4.8s) [20:24:27] >>> Job #804 claimed [20:24:27] Prompt: Triage this issue: auth middleware returns 403... [20:24:29] <<< Job #804 complete (exit 0, 1.2s) [20:24:34] Ready — waiting for jobs...|`
Google calls it:
"the shift from generative to agentic AI."
We just call it Tuesday.
ModelReins has been orchestrating multi-provider AI workforces while the industry was still writing trend reports about it.
Google Cloud AI Agent Trends 2026
Three steps
Run the server
Python + SQLite. Set a token, run python app.py. That's the control plane.
Connect workers
Install the SDK on any machine. npx modelreins-worker. It phones home and waits for work.
Dispatch jobs
Type a task in the dashboard. Pick a worker or let it auto-route. Output streams back in real time.
Capabilities
Multi-Agent Dispatch
Route tasks to any registered worker. Manual assignment or automatic.
Fleet Awareness
Define your infrastructure in YAML. Workers know what exists and what's healthy.
Context Policies
Control what each worker sees. Frontend tasks get URLs. Infra tasks get the map.
Secrets Brokering
Pointers, not passwords. Env vars or Vault. Workers get short-lived tokens.
Multi-Tenant RBAC
Complete data isolation. Admin, operator, viewer. Teams share one server safely.
Killswitch
File, URL, or dead man's switch. Halt all workers instantly. Independent of the server.
Signed Audit Trail
Every action HMAC-signed and logged. Verify integrity. Ship to your SIEM.
Zero-Knowledge Keys
Your API keys never touch the control plane. Workers fetch credentials locally.
Pricing
Free
$0/mo
-
2 workers
-
Unlimited jobs
-
Killswitch
-
Dashboard + streaming
-
Job chaining
-
Cost tracking
Start Free
Pro
$29/mo
-
10 workers
-
Unlimited jobs
-
Killswitch
-
Chain templates
-
Fleet context injection
-
Approval gates
-
Analytics dashboard
-
Priority support
Upgrade
Team
$79/mo
-
50 workers
-
Unlimited jobs
-
Killswitch
-
Chain templates
-
API access
-
Team members
-
Multi-user RBAC
-
Everything in Pro
Upgrade
Self-Hosted
Free
-
Unlimited everything
-
Your infrastructure
-
Full source (BSL 1.1)
-
Commercial license available
Source
Your agents. Your infrastructure. Your rules.
Start free. Upgrade when you need more workers.
Enterprise
Self-Hosted. Your Keys. Your Rules.
Run ModelReins on your own infrastructure. Bring your own API keys, keep data in-house, and manage AI workloads across teams with the controls you actually need.
-
Self-hosted deployment
-
Multi-tenant with role-based access
-
Fleet-aware worker routing
-
Approval gates and budget controls
-
SSO integration
-
Priority support and SLA
Let's Talk
Sign in to highlight and annotate this article

Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
model
The Minds Shaping AI: Meet the Keynote Speakers at ODSC AI East 2026
If you want to understand where AI is actually going, not just what’s trending, you look at who’s building it, scaling it, and questioning its limits. That’s exactly what the ODSC AI East 2026 keynote speakers lineup delivers. This year’s speakers span the full spectrum of AI: from foundational theory and cutting-edge research to enterprise deployment, governance, and workforce transformation. These are the people defining how AI moves from hype to real-world impact. Here’s who you’ll hear from and why missing them would mean missing where AI is headed next. The ODSC AI East 2026 Keynote Speakers Matt Sigelman, President at Burning Glass Institute Matt Sigelman is one of the foremost experts on labor market dynamics and the future of work. As President of the Burning Glass Institute, he ha

15 Datasets for Training and Evaluating AI Agents
Datasets for training and evaluating AI agents are the foundation of reliable agentic systems. Agents don’t magically work — they need structured data that teaches action-taking: tool calling, web interaction, and multi-step planning. Just as importantly, they need evaluation datasets that catch regressions before those failures hit production. This is where most teams struggle. A chat model can sound correct while failing at execution, like returning invalid JSON, calling the wrong API, clicking the wrong element, or generating code that doesn’t actually fix the issue. In agentic workflows, those small failures compound across steps, turning minor errors into broken pipelines. That’s why datasets for training and evaluating AI agents should be treated as infrastructure, not a one-time res
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models

Semantic matching in graph space without matrix computation and hallucinations and no GPU
Hello AI community,For the past few months, I’ve been rethinking how AI should process language and logic. Instead of relying on heavy matrix multiplications (Attention mechanisms) to statistically guess the next word inside an unexplainable black box, I asked a different question: What if concepts existed in a physical, multi-dimensional graph space where logic is visually traceable?I am excited to share our experimental architecture. To be absolutely clear: this is not a GraphRAG system built on top of an existing LLM. This is a standalone Native Graph Cognitive Engine.The Core Philosophy:Zero-Black-Box (Total Explainability): Modern LLMs are black boxes; you never truly know why they chose a specific token. Our engine is a “glass brain.” Every logical leap and every generated sentence i
b8679
llama-bench: add -fitc and -fitt to arguments ( #21304 ) llama-bench: add -fitc and -fitt to arguments update README.md address review comments update compare-llama-bench.py macOS/iOS: macOS Apple Silicon (arm64) macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.1 DLLs Windows x64 (Vulkan) Windows x64 (SYCL) Windows x64 (HIP) openEuler: openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph)

15 Datasets for Training and Evaluating AI Agents
Datasets for training and evaluating AI agents are the foundation of reliable agentic systems. Agents don’t magically work — they need structured data that teaches action-taking: tool calling, web interaction, and multi-step planning. Just as importantly, they need evaluation datasets that catch regressions before those failures hit production. This is where most teams struggle. A chat model can sound correct while failing at execution, like returning invalid JSON, calling the wrong API, clicking the wrong element, or generating code that doesn’t actually fix the issue. In agentic workflows, those small failures compound across steps, turning minor errors into broken pipelines. That’s why datasets for training and evaluating AI agents should be treated as infrastructure, not a one-time res

The Minds Shaping AI: Meet the Keynote Speakers at ODSC AI East 2026
If you want to understand where AI is actually going, not just what’s trending, you look at who’s building it, scaling it, and questioning its limits. That’s exactly what the ODSC AI East 2026 keynote speakers lineup delivers. This year’s speakers span the full spectrum of AI: from foundational theory and cutting-edge research to enterprise deployment, governance, and workforce transformation. These are the people defining how AI moves from hype to real-world impact. Here’s who you’ll hear from and why missing them would mean missing where AI is headed next. The ODSC AI East 2026 Keynote Speakers Matt Sigelman, President at Burning Glass Institute Matt Sigelman is one of the foremost experts on labor market dynamics and the future of work. As President of the Burning Glass Institute, he ha



Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!