Portkey
PulseAugur coverage of Portkey — every cluster mentioning Portkey across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Developer builds proxy to cut LLM API costs by routing to cheapest provider
A developer created an API proxy that routes requests to the most cost-effective LLM provider, aiming to reduce expenses for users. The proxy mimics OpenAI's API, allowing seamless integration with existing applications…
-
LLM invoices surge due to unmonitored agent loops and missing outcome assertions
LLM invoices are increasing significantly due to token consumption per task, not just per-token pricing. Observability platforms often fail to identify cost leaks because they don't track the actual business outcome of …
-
Bifrost gateway unifies VLM payloads for developers
A developer has created an open-source AI gateway called Bifrost to simplify interactions with multiple vision-language models (VLMs). The gateway standardizes image payload formatting, allowing a single request structu…
-
Dev team hit by silent LLM provider model drift
A software engineering team experienced a significant drop in their automated regression evaluation scores due to silent model updates from a third-party provider. The team discovered that the model they were using was …
-
Buildkite uses multi-LLM gateway to ensure feature uptime
Buildkite's engineering team implemented a strategy to maintain service availability for their natural language build query feature, despite relying on external LLM providers. They deployed a gateway called Bifrost, whi…
-
Dev team uses Bifrost gateway to overcome Anthropic API rate limits
A software engineering team encountered frequent rate limiting errors from Anthropic's API during peak hours for their internal PR-review bot. To resolve this, they implemented Bifrost, an API gateway, to manage multipl…
-
Nexus Labs replaces 60% of LLM middleware with Bifrost virtual keys
Nexus Labs significantly reduced its custom LLM middleware by replacing over 60% of its 11,247 lines of Python code with Bifrost's virtual key system. This change streamlined per-tenant cost attribution, rate limiting, …
-
Prophesee uses Bifrost to cap VLM spend for CV researchers
A computer vision research team at Prophesee implemented a system called Bifrost to manage their spending on large language models (LLMs) for dataset annotation. The team was experiencing high, uncontrolled costs due to…
-
Company Chaos Tests LLM API Calls, Finds Costly Failures
A company experienced significant cost overruns and build time delays due to unmanaged LLM API calls within their CI/CD pipeline. Injecting failures into their Buildkite agent fleet revealed that default SDK retry logic…
-
Bifrost gateway improves LLM cost, data quality for robotics and agents
Two separate teams at Nexus Labs and Prophesee have adopted Bifrost, an open-source gateway, to manage their interactions with multiple large language models. Prophesee used Bifrost to caption 1.2 million robotics frame…
-
AI agent spending needs pre-call budget enforcement
A new approach is needed to govern spending on AI agents, as current token counters and observability tools are insufficient. The proposed solution involves implementing a pre-call budget enforcement system, similar to …
-
STRIDE-GPT tool models AI app threats, logs context, limits tokens
STRIDE-GPT is an open-source tool designed to generate STRIDE threat models for AI applications by analyzing architecture descriptions. It emphasizes treating LLM-specific assets like system prompts, RAG documents, and …
-
Palo Alto Networks acquires Portkey to secure AI agents with new AI Gateway
Palo Alto Networks has acquired Portkey, a company specializing in AI security gateways. This acquisition aims to enhance the security of AI agents by integrating Portkey's technology into Palo Alto Networks' offerings.…
-
Malicious AI extensions pose threat; Palo Alto Networks buys AI security firm
Cybersecurity researchers have identified over 18 malicious AI browser extensions that pose as productivity tools but function as Remote Access Trojans (RATs) and infostealers. These extensions are designed to steal sen…
-
Measuring AI Gateway Failover: 30 Days of Production Data
Anthropic has released an update on Claude's sycophancy, noting that Opus 4.7 shows a 50% reduction in sycophantic responses compared to Opus 4.6, particularly in relationship guidance conversations. The company also de…
-
Google unveils agent memory framework; DeepSeek releases cost-effective V4 models
Google Research has introduced ReasoningBank, a novel framework designed to enhance AI agents' ability to learn from their experiences, both successes and failures, after deployment. This system distills generalizable r…