标签：#c

Most agent projects do not fail because the first model call is difficult. They become difficult when the prototype needs memory, tools, evaluation, a user interface, documentation that coding agents can navigate, and a repeatable review process. That is the problem the open-source AgentsKit ecosystem is trying to solve for JavaScript teams. It is a set of independent projects with shared contracts, rather than one application that must own the whole stack. The six public pieces 1. AgentsKit: the composable foundation AgentsKit provides focused JavaScript and TypeScript packages for runtimes, adapters, tools, skills, memory, RAG, evaluation, observability, sandboxing, and UI bindings. Its core has zero runtime dependencies and a CI-enforced 10 KB gzipped budget. Six formal contracts keep adapters, tools, memory, retrievers, skills, and runtimes substitutable. You can run a first local agent without an API key: npm install @agentskit/core @agentskit/runtime tsx Then connect OpenAI, Anthropic, Gemini, Ollama, or another adapter without changing the rest of the runtime composition. 2. AgentsKit Chat: one interaction model, seven renderers AgentsKit Chat defines an interactive agent experience once and renders it through React, React Native, Ink, Vue, Svelte, Solid, or Angular. It also supports deterministic local answers before an optional backend call. That matters for documentation and support interfaces where exact project facts should not require an LLM. pnpm dlx @agentskit/chat-cli@0.4.0 init my-chat --renderer react --yes 3. Registry: reusable source, not another dependency The AgentsKit Registry distributes ready-to-use agents in a shadcn-style model: the CLI copies the source into your project, so you can inspect and modify it. npx agentskit add research npx agentskit add code-review The public catalog currently includes research, code-review, and knowledge-promotion agents, and is open to contributions. 4. Agents Playbook: engineering rules that can execute Ag

Two substantial slices of gene/phen trait implementation just landed on submain . This shifts the needle significantly—contract checking and the capability for phen methods to actually get called at runtime are in the door. Previously, we only had the basic declarations and coherence working but now methods can type-check, Self can resolve per receiver, and calls execute. The submain branch now sits 15 commits ahead of main , holding the matrix at 321/0. Contract Checking and Self Resolution (Slice 2) Let's zero in on commit fcd3193 , which makes waves with 594 insertions across 23 files. The big takeaway is Pass 0 contract conformance. The collect_gene_phen_registry() function now actively validates every phen against its gene. Consider everything from arity to positional parameter types (post- Self substitution), return types, and even checks for both missing and extra methods. If there's a mismatch, it doesn’t just shout—each one is a precise diagnostic identifying gene, method, position, and expected-vs-actual types. It's pinpoint troubleshooting. The decision to resolve Self at the concrete level before analysis was deliberate. Self in phen signatures and bodies changes to the actual receiver type within the AST thanks to substitute_self_type() . This function even navigates through intricate structures like Array , Handle , and Result wrappers. There was an alternative: treating Self as a floating type parameter. But honestly, it doesn't cut it because types_compatible would unify any type param with anything. Sticking to the design docs, our path— Self is concrete, not a floating parametric. How about ownership? It's strict. There's no room for unauthorized methods beyond the gene's contract. And we're talking multiple enforcement points: from Pass 0 checks to the phen_methods field on Analyzer triggered during per-file analysis, down to cross-gene-method name collisions caught by Pass 0. Every path specified is locked down, as envisioned by the design docs.

Most agent tutorials stop at tools: give the model a function schema, hope it calls the right one. That works for get_time and hash_string . It falls apart when the model skips a knowledge search and opens a ticket, or when eighty APIs all land in one context window. Solon AI keeps tools as the execution unit, then adds Talent as the product unit: tools plus SOP plus activation rules. Think of it this way: Tool ≈ a function Talent ≈ a class that owns those functions, their playbook, and when they appear This post is a practical map of when to stay on tools, when to wrap them in a talent, and how registration actually works in Solon v4.0.3. The product failure behind “just add more tools” Bare tools only answer two questions for the model: what can I call? what args does it need? They do not answer: should this capability even be visible right now? what order must I follow before a dangerous call? which tools belong to the same business domain? That gap shows up as: premature side effects (ticket created before diagnosis) context blow-up (full tool tables on every turn) weak SOP compliance (model freestyles across domains) Talent is Solon’s answer: a reusable package of awareness + instruction + tools , with automatic coloring so tools keep their domain identity. Tool vs Talent in one table From the official comparison: Dimension Tool ( FunctionTool ) Talent ( Talent ) Unit Single function / method Instruction + tool set + state Abstraction Physical: how Logical: when and under which SOP Context awareness Passive isSupported(Prompt) can activate or hide Injected content Tool schema (JSON) System prompt fragment + tool list Constraint strength Weak — model freestyles from description Strong — SOP via getInstruction Registration defaultToolAdd / toolAdd defaultTalentAdd / talentAdd They are not rivals. A talent contains tools. Registering a talent also registers its tools; you do not need a second defaultToolAdd for the same set. Lifecycle: what actually runs at reques

Open source web terminal multiplexer for AI agents Discussion | Link

The Range Rover GT will debut as an EV with a hybrid version to follow.

It’s “the most car-like Range Rover ever created,” but will this all-electric grand tourer spoil Jaguar’s Type 01 party?

Hey HN, I built Superserve, a compute layer that lets AI agents live inside isolated Firecracker microVMs with no session time limits. The problem I kept running into: most sandbox providers kill your agent after 24 hours. If you're running something autonomous that needs to work for days — refactoring a codebase, running tests in a loop — you're constantly fighting timeouts and rebuilding state. Superserve lets you snapshot a running VM at any point, fork it into parallel branches, and resume e

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.