TrueFoundry is a unified platform with an enterprise-grade AI Gateway - combining LLM, MCP, and Agent Gateway to securely manage, route, and govern AI workloads
San Francisco
Joined April 2022
- Tweets445
- Following58
- Followers1.2K
- Likes338
TrueFoundry now integrates with @confident_ai.
Teams routing LLM traffic through the TrueFoundry AI Gateway can now send every request to Confident AI as an OpenTelemetry trace and score it with online evaluations: answer relevancy, faithfulness, toxicity, and PII leakage, all running on live production traffic, with zero tracing code in your applications.
Evaluation runs asynchronously, off the request path, so it adds no latency to user-facing calls. Combined with TrueFoundry’s unified access to 1,000+ LLMs, rate limiting, cost tracking, and governance, teams get one place to route every model call and see how good each answer actually was, with quality scores sitting right next to latency and cost.
One gateway. Every request, evaluated.
Thanks to the @confident_ai for the collaboration!
🤖 Made with AI
The Decisions API is live on TrueFoundry AI Gateway: ask typed yes/no, choice and score questions, get probabilities back. 7 providers, 2 routes: /v1/decisions and /v1/systemone. Same keys; switch provider by changing the model string. Read more: truefoundry.com/blog/blog-de…
3/ Limits to plan for: no streaming. Image input works only with OpenAI models on /v1/decisions. Self-hosted vLLM answers choice questions only.
4/ Tracing, cost tracking (input tokens only), budgets and rate limits apply as for any model, and a virtual model can fail over across OpenAI and System One targets. Docs: truefoundry.com/docs/ai-gate…
Here's OperatorOS, the first-place build from our recent #AgentsThatAct hackathon, in action 🎬
Neighborhood store owners in India spend hours every day reconciling cash, restocking, chasing customer credit and running promotions, across tools that mostly only speak English.
Our first-place winners built a multilingual agent that runs that whole process end-to-end, by voice.
The entire workflow was built on the TrueForge Agent Harness and TrueFoundry AI Gateway.
How to switch: tick the model in Models Selection, set Access Control, swap the model string. Nothing else changes.
Read more here :truefoundry.com/blog/gpt-6-1…
Where it fits: GPT-6 Luna for simple requests, GPT-6.1 Sol for medium, GPT-6 Astra for the hard tail, one virtual model with Auto Routing in front. Pricing is public at truefoundry.com/models.
@truefoundry now integrates with @Onyx_Security.
Teams routing LLM traffic through the TrueFoundry AI Gateway can now add Onyx runtime protection as a custom guardrail: prompt-injection defense, jailbreak detection, data-exfiltration checks, and content policies enforced on every prompt and response, with zero changes to application code.
Combined with TrueFoundry's unified access to 1,000+ LLMs, rate limiting, cost tracking, and governance, teams can apply one security policy across every app and model, with every block traced alongside the rest of the request.
One gateway. Runtime protection for every LLM call.
Thanks to the @Onyx_Security team for the collaboration!
Build Agents That Act is live at Polaris Campus, Bangalore.
900+ Round 1 registrations, one day, every agent on TrueForge. With @polariscodes.
The bar: reach a real system, run it live in front of the judges, stop before anything irreversible.
Updates below 👇 #agentsthatact
A researcher who built using TrueForge a Proof layer for Academic papers which not only checks sources but also rechecks validity of the claims and proofs in the paper .
A team from First Year is here to build an agent using TrueForge that detects bugs and saves precious development time !
As anyone who is familiar with the SDLC will tell you , Quality Assurance is an essential part of releasing any product . TrueForge can make this simpler and help QA professionals save time and effort!
How to make underwriting better and reduce time for Loan Providers , a real Financial industry problem solved using TrueForge