Frank Chen

@RespanAI Respan is everything you need for AI internal tooling m

AI observability platforms raised $1B+ to reinvent print debugging for the agent era. Reading traces manually is not a scalable production workflow. We think the stack should catch issues itself. Meet Respan.

@Chillwithmeii @RespanAI We’re OTEL-native, but still fully customizable!

@RespanAI otel or custom spans? need loop viz

Tracing built for agents in production.

Doing a smog check today and realized California really said: “Your car seems fine, but prove it.” Honestly, AI apps need the same energy. Your agent might look fine in demo, but in production you still need to prove: latency isn’t creeping up cost isn’t randomly spiking tool calls aren’t silently failing answers aren’t getting worse after a prompt change The vibe is not “trust me bro, it works", and that’s what we’re building at respan.ai

@hridoyreh cc ask me to go to sleep

📂 SEO ┃ ┣ 📂 Strategy ┃ ┣ 📂 Keyword Research ┃ ┣ 📂 Search Intent ┃ ┣ 📂 Competitor Analysis ┃ ┣ 📂 Keyword Clustering ┃ ┗ 📂 SEO Wins ┃ ┣ 📂 On-page SEO ┃ ┣ 📂 Title ┃ ┣ 📂 Descriptions ┃ ┣ 📂 Header Structure ┃ ┣ 📂 URL Structure ┃ ┣ 📂 Internal Linking ┃ ┣ 📂 Image Optimization ┃ ┗ 📂 Content Optimization ┃ ┣ 📂 Technical_SEO ┃ ┣ 📂 Crawlability ┃ ┣ 📂 Indexing ┃ ┣ 📂 Site Speed ┃ ┣ 📂 Schema Markup ┃ ┣ 📂 Canonical Tags ┃ ┗ 📂 XML Sitemaps ┃ ┣ 📂 Content SEO ┃ ┣ 📂 Blog Content ┃ ┣ 📂 Pillar Pages ┃ ┣ 📂 Topic Clusters ┃ ┣ 📂 Tools Content ┃ ┣ 📂 Evergreen Content ┃ ┣ 📂 Programmatic SEO ┃ ┗ 📂 Content Refresh ┃ ┣ 📂 Off-page SEO ┃ ┣ 📂 Link Building ┃ ┣ 📂 Guest Posting ┃ ┣ 📂 Digital PR ┃ ┣ 📂 Brand Mentions ┃ ┗ 📂 Outreach ┃ ┣ 📂 International SEO ┃ ┣ 📂 Hreflang ┃ ┣ 📂 Multi Language ┃ ┣ 📂 Geo Targeting ┃ ┗ 📂 Localization ┃ ┣ 📂 Analytics ┃ ┣ 📂 Google Analytics ┃ ┣ 📂 Search Console ┃ ┣ 📂 Rank Tracking ┃ ┣ 📂 Traffic Analysis ┃ ┗ 📂 KPI Tracking ┃ ┣ 📂 UX ┃ ┣ 📂 Page Speed UX ┃ ┣ 📂 Mobile Optimization ┃ ┣ 📂 UX Design ┃ ┣ 📂 A/B Testing ┃ ┗ 📂 Conversion Funnels ┃ ┣ 📂 AI SEO ┃ ┣ 📂 Content Optimization ┃ ┣ 📂 NLP Optimization ┃ ┣ 📂 Generative SEO ┃ ┣ 📂 SERP Features ┃ ┗ 📂 LLM Visibility ┃ ┗ 📂 Growth ┣ 📂 Topical Authority ┣ 📂 Content Scaling ┣ 📂 Link Acquisition ┗ 📂 SEO Experiments

Working on SEO with claude code now it's so considerate😂

check it out here: respan.ai/docs/integrati…

Interesting. This is also what we support at @RespanAI. Most gateways like OpenRouter use router-style APIs that normalize requests into an OpenAI format. That can change behavior or drop provider-specific features. Respan is different. We provide a true pass-through gateway, so requests, headers, and streaming are forwarded as-is. Agent CLIs behave exactly the same as calling the provider directly. In addition, we also log all calls for observability and debugging. (PS. we also support Codex, Gemini CLI , and OpenCode)

@diwanksingh @memorydotstore @ycombinator @kul @t_blom @IshitaJindal17 Congrats!

exceited to announce that @memorydotstore is part of the @ycombinator P26 batch 🟧 with @kul and @t_blom as our partners one shared memory for your team's agents! if you are building agents and think memory, talk to @IshitaJindal17 and I

@RespanAI limits are really important guardrails at API level but most gateway providers don't support this.

Respan Launch Week, Day 5 🚀 Introducing AI Gateway Limits and Alerts. LLM costs can get out of control fast in production, especially as traffic grows across models, API keys, and apps. Now you can set limits directly in Respan AI Gateway: - Alerts via email or Slack - Recurring budgets for LLM usage - Limits by API key or model - Controls for cost, requests, or tokens When a limit is exceeded, you can block the request or send a warning. Built for teams that want to move fast with clear cost controls. Try it today!

Respan Launch Week, Day 4: Introducing Respan Integrations Most teams still spend days setting up observability. That’s why we invested heavily in Respan Integrations. We support major LLM and agent frameworks like OpenAI, Anthropic, Gemini, LangChain, Vercel AI, and Pydantic AI, with more being added. Run 'npx [at]respan/cli setup' and start tracing in minutes, not days.

The cake is 🐐

Respan Launch Week, Day 3: introducing @RespanAI Agent, CLI, and MCP. Three ways to stop doing AI engineering by hand: → Agent: ask it to build an evaluator, fix a prompt, or find the root cause of a bad trace on the platform. → CLI: npx respan@cli setup - auth, framework detection, and tracing in one command. → MCP: plug Respan into Claude Code, Cursor, or anything that speaks MCP. Same data, same access, wherever you work.

@RespanAI Evals shouldn’t feel like guesswork🥳

Respan Launch Week, Day 2: Evals Evals are one of the hardest parts of building AI applications. It is not because teams cannot run them. It is because they are hard to structure, hard to compare, and even harder to improve over time. So teams end up guessing. Did this prompt actually get better? Is this model really an improvement? We built Evals in Respan to make this systematic. You define: - what you want to test, such as prompts, models, or configs - the dataset, from production logs or test cases - the evaluators, whether LLM, code, human, or a mix Then you run experiments and compare results side by side. Same inputs. Same evaluation. Clear answers. No more guessing. Start running your first eval.

@HendrixLiu29208 really helps a lot for catching issues early

Respan Launch Week, Day 1: we’re launching Monitors for AI products. AI teams already track the basics in production: - error rate - cost - latency - token usage The problem is not measuring them. The problem is reacting fast enough. A model update can increase error rate. A prompt change can raise cost. Latency can drift over time. Most teams do not catch these problems right away. Monitors turn these metrics into real-time alerts. You set the thresholds that matter, and get notified as soon as something crosses the line. This gives teams a faster way to spot issues and respond before they grow. Activate your first monitor now.

|￣￣￣￣￣￣￣￣￣￣￣￣ | we believe knowing what your agent did in production means seeing every prompt, tool call, and response with full context |＿＿＿＿＿＿＿＿＿＿＿＿| \ (•◡•) / \ / —— | | |_ |

Evals are hard, so we built a SCRATCH to solve it.