TrueFoundry now integrates with @straikerai .
Teams routing LLM and agent traffic through the TrueFoundry AI Gateway can now add Straiker as a guardrail that checks every prompt on the way in and every model response on the way out: prompt injection, manipulated agents, risky tep attacks that don’t fit inside a single request, all enforced at the gateway, with no adapter to build and no changes to application code.
Security teams set the controls per agent in the Straiker console. Straiker returns an allow-or-block verdict in under 300 ms, and the gateway enforces it. Start in Audit mode to see what gets flagged, flip to Enforce when it looks right, and every check shows up in TrueFoundry’s request traces. Combined with TrueFoundry’s unified access to 2,500+ LLMs, rate limiting, cost tracking, and governance, platform teams keep one governed gateway and application teams ship agents without rebuilding security in each one.
One gateway. Every request, protected.
Thanks to the @straikerai team for the collaboration!
Teams routing LLM and agent traffic through the TrueFoundry AI Gateway can now add Straiker as a guardrail that checks every prompt on the way in and every model response on the way out: prompt injection, manipulated agents, risky tep attacks that don’t fit inside a single request, all enforced at the gateway, with no adapter to build and no changes to application code.
Security teams set the controls per agent in the Straiker console. Straiker returns an allow-or-block verdict in under 300 ms, and the gateway enforces it. Start in Audit mode to see what gets flagged, flip to Enforce when it looks right, and every check shows up in TrueFoundry’s request traces. Combined with TrueFoundry’s unified access to 2,500+ LLMs, rate limiting, cost tracking, and governance, platform teams keep one governed gateway and application teams ship agents without rebuilding security in each one.
One gateway. Every request, protected.
Thanks to the @straikerai team for the collaboration!
1
0
3
140
Something big is coming on 10 November 👀
On Tuesday, we start a new chapter for TrueFoundry, and it’s one we’ve been looking forward to for a long time. If you look after AI at your company, this one might be interesting.
On Tuesday, we start a new chapter for TrueFoundry, and it’s one we’ve been looking forward to for a long time. If you look after AI at your company, this one might be interesting.
0
2
4
355
TrueFoundry retweeted
tomorrow: watch an agent fix itself, live 🎃
Anant Agarwal (@truefoundry) builds a TrueForge agent that fails, reads its own runs and rewrites itself to beat run 1.
30 min, online. bring your stuck agent.
tue 8:30pm SF 🇺🇸 · wed 3:30pm Melbourne 🇦🇺 · wed 10am Bangalore 🇮🇳
join FZpNO
Anant Agarwal (@truefoundry) builds a TrueForge agent that fails, reads its own runs and rewrites itself to beat run 1.
30 min, online. bring your stuck agent.
tue 8:30pm SF 🇺🇸 · wed 3:30pm Melbourne 🇦🇺 · wed 10am Bangalore 🇮🇳
join FZpNO
0
2
7
409
TrueFoundry retweeted
Code. Create. Compete!
Join the TrueFoundry Forge-A-Thon at Techfest, IIT Bombay and build AI-powered coding agents.
🏆 Prize Pool: ₹3,00,000
Register now: techfest.org/competitions
#Techfest #AI #Hackathon #IITB
Join the TrueFoundry Forge-A-Thon at Techfest, IIT Bombay and build AI-powered coding agents.
🏆 Prize Pool: ₹3,00,000
Register now: techfest.org/competitions
#Techfest #AI #Hackathon #IITB
0
8
8
449
Our TrueForge challenge at Stranger Builds, NERDCONF's Halloween hackathon: build an agent that scores itself, rewrites its own skills, and beats run 1 on a later run.
USD 10K in prizes and credits. Sat 31 Oct in person or online, then 7 days to ship.
Registration link below!
USD 10K in prizes and credits. Sat 31 Oct in person or online, then 7 days to ship.
Registration link below!
1
0
1
187
We're running a TrueForge track at Stranger builds: build a self-improving agent 🔁
an agent that gets better every run beats one that's perfect on day one. show us yours.
See you Saturday!
an agent that gets better every run beats one that's perfect on day one. show us yours.
See you Saturday!
zero users is a bug. you have 7 days 🎃
stranger builds starts saturday: SF 🇺🇸 Melbourne 🇦🇺 Bangalore 🇮🇳 online 🌍
fix a problem, get your first users. $10K in prizes and credits
thank you @Fetch_ai @Base44 @VonageDev, @truefoundry (TrueForge) and @ASILab for betting on nerds sers will love this, send it over! 👀
0
1
6
227
Agent Identity is live on TrueFoundry 🔐
Every AI agent gets its own verifiable identity, enforced at the gateway that already runs your LLM and MCP traffic. No shared keys. No auth code in your agents.
Every AI agent gets its own verifiable identity, enforced at the gateway that already runs your LLM and MCP traffic. No shared keys. No auth code in your agents.
2
0
2
199
Now you can decide who can call each agent and what each agent can call. Works with agents on Bedrock AgentCore, Vertex AI, LangGraph and your own services.
0
0
0
35
Multi-agent chains lose the user by hop three.
Agent Identity lets you choose how identity flows at each hop: pass-through, client credentials, on-behalf-of token exchange (Entra + Okta) or AWS SigV4.
Agent Identity lets you choose how identity flows at each hop: pass-through, client credentials, on-behalf-of token exchange (Entra + Okta) or AWS SigV4.
0
0
0
31
GPT-6.1 Terra is live on TrueFoundry AI Gateway.
$1 / $5 per 1M tokens, half of GPT-6.1 Sol. 1.05M-token context, 128K output.
Model string: openai/gpt-6.1-terra. Same endpoint, same keys.
Read more : truefoundry.com/blog/gpt-6-1-t…
$1 / $5 per 1M tokens, half of GPT-6.1 Sol. 1.05M-token context, 128K output.
Model string: openai/gpt-6.1-terra. Same endpoint, same keys.
Read more : truefoundry.com/blog/gpt-6-1-t…
1
0
0
143
How to switch: tick the model in Models Selection, set Access Control, swap the model string. Nothing else changes. OpenRouter and AWS Bedrock (global and US profiles) are in the catalog now; OpenAI direct and Azure entries will follow.
1
0
0
71
Where it fits: Terra for the broad middle of your traffic, Sol for the hard tail, one virtual model with Auto Routing in front. Pricing is public at truefoundry.com/models.
0
0
0
24
₹3L in prizes + PPIs, up for grabs. 🏆
The TrueFoundry Forge-a-thon is live at @Techfest_IITB .Build, deploy and scale AI agents with TrueForge.
Open to students and working professionals. Grand Finale: Dec 2026.
Registration link in comments .
The TrueFoundry Forge-a-thon is live at @Techfest_IITB .Build, deploy and scale AI agents with TrueForge.
Open to students and working professionals. Grand Finale: Dec 2026.
Registration link in comments .
1
1
2
183
TrueFoundry retweeted
The AI Founders 100 — India’s Rising Leaders Building the Future with AI
Read More: tinyurl.com/5n7aymf7
Read More: tinyurl.com/5n7aymf7
0
2
4
132
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 ion 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!
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 ion 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!
0
2
1
198
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-deci…
1
1
1
185
3/ Limits to plan for: no streaming. Image input works only with OpenAI models on /v1/decisions. Self-hosted vLLM answers choice questions only.
1
0
0
44
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-gatewa…
0
0
0
28