今日已更新 63 条资讯 | 累计 20533 条内容
关于我们

标签：#opensource

找到 1366 篇相关文章

AI 资讯

Two undocumented bugs in MCP Apps I found building a task panel for Claude

I spent a week building Wingman , an open source MCP server that renders a persistent task panel inline in Claude conversations using MCP Apps (SEP-1865). The spec is solid. The SDK is solid. But I hit two bugs that cost me most of a weekend each, and neither is documented anywhere I could find. Writing them up here in case they save someone else the time. Bug 1: resourceUri has two valid-looking locations, and only one works MCP Apps needs a way to tell the host "render this resource as a UI for this tool call." That pointer lives in _meta.ui.resourceUri . The question is: meta on what? I started with a parameterized resource template, ui://wingman/panel/{plan_name} , registered per plan. That was my first mistake. Parameterized templates get listed under resources/templates/list , not resources/list , and hosts do not prefetch or render anything from the templates list. The fix was straightforward once I found it: register one static resource, ui://wingman/panel , and pass the actual plan data through structuredContent on the tool result instead of baking it into the URI. That fix surfaced the real bug. My show_plan tool was returning a plain Python dict: return { " plan " : plan_data , " _meta " : { " ui " : { " resourceUri " : " ui://wingman/panel " }} } This looks correct. It is not. FastMCP's result conversion takes a returned dict and serializes the whole thing into structuredContent , verbatim, including any _meta key the dict happens to carry. So the actual wire result looked like this: result . structuredContent [ " _meta " ][ " ui " ][ " resourceUri " ] # == "ui://wingman/panel", but wrong place result . meta # None — this is what the host actually reads MCP Apps hosts read resourceUri off the top-level _meta on the CallToolResult , not off whatever ended up inside structuredContent . With that pointer effectively missing, the host had nowhere to bind the iframe. The visible symptom was strange: actions in the UI would update on screen but nothing persist

2026-06-23 原文 →
AI 资讯

I got tired of rewriting the same AI boilerplate so I built a library to fix it

Every time I added AI to a React app, I rewrote the same 200+ lines. Streaming loop. Manual message history. Tool call orchestration. Error handling. setIsLoading(false) only if I remembered. After the third project I stopped and asked: why is nobody solving this the way RTK Query solved REST APIs? So I built Strand ( https://github.com/strand-js/strand ). Before const [messages, setMessages] = useState([]) const [isLoading, setIsLoading] = useState(false) async function send(text) { setIsLoading(true) manually stream tokens manually detect tool calls manually loop until done setIsLoading(false) only if you remembered } After const { messages, send, isPending, isStreaming, cancel } = useConversation({ system: 'You are a helpful assistant.', }) Streaming, history, tool calls, cancellation, retry; all handled. The thing nobody else has: useToolCall Works from ANY component; no prop drilling function WeatherStatus() { const { status, input, output } = useToolCall('get_weather') if (status === 'running') return <div>Checking {input?.location}…</div> if (status === 'done') return <div>{output?.temp}°F</div> return null } Live tool state: pending → running → done. Its observable anywhere in your tree. Fixing the isLoading design flaw The Vercel AI SDK has 4+ open issues ( https://github.com/vercel/ai/issues ) about isLoading getting stuck. The reason is architectural because "request sent" and "tokens arriving" are different states. Strand tracks four: const { isPending, isStreaming, isDone, error } = useConversation() // isPending: waiting for first token // isStreaming: tokens arriving // isDone: just completed // error: something failed Works with Anthropic, OpenAI, and Google Gemini npm install @strand-js/core @strand-js/react zod npm install @strand-js/anthropic # or openai, or google Swap providers by changing one server import. Zero frontend changes. v0.1.8, MIT, open source. → https://github.com/strand-js/strand

2026-06-23 原文 →
AI 资讯

How Much Does It Actually Cost to Run a Local LLM? (€ per Million Tokens, Measured)

"It runs on my own GPU, so it's basically free." I believed that until I put a meter on it. So I ran a controlled benchmark on one box — an openSUSE machine with a single RTX 3090 — driving three local models through ollama under an identical fixed workload (256-token generations in a loop for ~4 minutes each), while my open-source dashboard priced every run by the real GPU energy it burned : power sampled from nvidia-smi every 10 s, integrated over each run's exact window, multiplied by my actual day/night tariff. One number per model, in euros per million output tokens. Here's the part that made me re-run it. The tiny gemma3:1b came out at €0.118 / 1M tokens — about 5× cheaper than a hosted Flash-class API (~€0.55). But gemma3:27b 's electricity alone was €0.706 / 1M — more expensive per token than just paying the cloud, and that's before a single cent of the GPU's purchase price. "Local" didn't make it cheaper; it made it cost more and I own the depreciation. The mechanism is one line: each token costs watts ÷ throughput , and a big dense model is both slow and thirsty. A newer mid-size architecture ( gemma4:26b ) bought a lot of that back, landing at €0.272 . The full guide is methodology-first and reproducible end to end — minting an ingest key, the stdlib-only client, the exact ollama loop that reads eval_count / eval_duration for real tokens-per-second, reading each run back priced, and the honest caveats (this is marginal GPU energy only — not capex, idle, or cooling — and the absolute numbers round to fractions of a cent; the shape is the finding). Read the full guide on Medium → https://medium.com/@arsen.apostolov/how-much-does-it-actually-cost-to-run-a-local-llm-per-million-tokens-measured-4a90a7f31a48

2026-06-23 原文 →
AI 资讯

How I Stopped Duplicating AI Skills Across Claude Code, Cursor, Codex, Gemini CLI, and Other Tools

Has anyone else ended up maintaining the same AI skill in multiple places? I use Claude Code, Codex, Cursor, Gemini CLI, Kimi, and several other AI tools. Over time, I accumulated a huge collection of skills and workflows. The annoying part wasn't creating them. It was keeping them synchronized. A skill would exist in one format for Claude Code, another for Cursor, another for Gemini, and so on. Eventually, I got tired of duplicating everything and built an open-source project called AI Omni Skills. The idea is to keep a single source of truth and generate the formats required by different AI tools. Now I update a skill once and regenerate whatever structure a specific tool expects. I'm curious: How are you managing skills today? Are you duplicating them across tools? What integrations would you want to see? Repo: https://github.com/moatazhamada/ai-omni-skills

2026-06-22 原文 →
AI 资讯

Trust the harness, not the model: a weekend of local agents building their own guardrails

Cross-posted from the LLMKube blog . A local 27B coding model, running on hardware in my house, is a coin flip. Some runs it nails the fix in twenty minutes. Some runs it edits the wrong file, writes a test that passes no matter what the code does, and tells you it's done. The bet behind LLMKube's Foreman was never that I would find a local model good enough to trust. It was that I could build a harness I trust more than any single model's output. This weekend tested that bet harder than any benchmark could, because the harness spent the weekend building its own guardrails. Here is the short version of what happened across 0.8.12 and 0.8.13. My local coder built three new gates for itself. One of them shipped with the exact flaw it was written to catch, and the review caught it. Three new contributors sent four clean pull requests while the machines worked. The same model ran on an AMD box and an Apple Silicon Mac, and the Mac quietly won a round nobody expected. And not one byte of any of it touched a cloud API. The thesis, stated plainly Trust the harness, not the model. A coding agent on a local model produces output of wildly variable quality, and no amount of prompt tuning makes a 27B as reliable as a frontier model. So Foreman does not ask the model to be reliable. It wraps the model in a pipeline that is : the coder works in a cloned workspace, a fast in-workspace gate runs gofmt, vet, build, lint, and the unit tests for the packages it touched; a reviewer reads the diff against the issue; and a clean-room Kubernetes Job re-runs the full suite before anything is allowed to call itself a GO. Around all of that sit deterministic rails: scope checks, edit-free-streak detection, repo-map context. The model is a stochastic component inside a system whose job is to make the system's verdict trustworthy even when the component is not. The interesting question is never "is the model good." It is "does the harness catch the model when it is bad." This weekend gave me

2026-06-22 原文 →
AI 资讯

I Built RAG From Scratch in Python to Understand It. Here's What I Learned.

I had used LangChain's RAG chain in production for six months. I could not have told you, off the top of my head, what chunk_overlap did, or why cosine similarity is the right distance metric, or how nomic-embed-text actually turns a sentence into a vector. The high-level library abstracted all of it away. So one weekend I deleted the LangChain dependency and wrote a RAG pipeline from scratch in ~500 lines of plain Python. No framework, no magic. pypdf for text extraction. A 60-line chunker. ChromaDB for the vector store. Ollama for embeddings and the LLM. The whole thing is on GitHub — every module is under 200 lines, every test is deterministic, and you can read the whole thing in one sitting. This is the build log. Not a tutorial — the build log, with the parts that surprised me and the parts I got wrong the first time. Why bother The honest reason: I was using LangChain's RetrievalQA chain and getting answers I didn't trust. Sometimes the model would say "according to the document" when the document didn't say that. Sometimes the citations were wrong. I had no way to know if the chunker was dropping important context, or if the cosine similarity was picking the wrong neighbors, or if the prompt was actually constraining the model. The library was a black box. When you build it yourself, every layer is inspectable. When the answer is wrong, you can add a print statement in pipeline.py line 102 and see exactly which chunks were sent to the LLM. When the chunker cuts a sentence in half, you see it in the test fixtures. When the embedding model gives garbage for some inputs, you can swap in a different model with one constructor parameter. None of that is possible when the whole thing is RetrievalQA.from_chain_type(llm=..., retriever=...) . The other reason: the code I wrote is 500 lines, and it covers the same ground as a 50-line LangChain script. The extra 450 lines are comments, type hints, tests, and explicit error handling. That's the actual complexity. LangCha

2026-06-22 原文 →
AI 资讯

When AI Agents Start Working Together: Three Challenges No One Talks About

The trajectory of AI agents over the past two years has been remarkably clear: from single-purpose tools to personal assistants. Everyone runs their own agent, feeds it tasks, gets results back. It works well for individual productivity. Then comes the question every team eventually asks: can these agents work together? The answer is yes, but the problems you encounter along the way are rarely the ones you expected. They aren't about model capabilities or prompt engineering. They're about communication, context, and coordination — the same class of problems that distributed systems engineers have been solving for decades, now showing up in a new form. Here are three challenges that caught us off guard when we started building agent collaboration into Octo , an open-source workplace platform where AI agents and humans share the same communication space. Challenge 1: Context Visibility Boundaries When you use an agent personally, context management is straightforward. You decide what information the agent sees; its output comes back to you. The boundary is clean — it's just your workspace. In a team setting, that boundary dissolves. One of the first issues we ran into was surprisingly simple. We had an agent summarizing discussions across several channels. During testing it started pulling roadmap discussions from a product channel into an engineering planning thread. Nothing sensitive leaked externally, but it immediately exposed how unclear our context boundaries were. Traditional software handles this through API gateways, data permissions, and microservice boundaries. But agent context isn't just structured data — it includes conversation history, reasoning chains, and intermediate states. An agent's thought process during a task is valuable context, but it might also contain information that shouldn't cross team boundaries. What you need is fine-grained context visibility control. Not "everything open" or "everything closed," but dynamic rules that determine whic

2026-06-22 原文 →
← 上一页 下一页 →