anvia-agent
Build Anvia agents and tools — Agent options, tool definitions, approvals, memory, streaming, multi-agent teams, and provider wiring.
Skill by anvia-hq
Chalk Labs
Need help deploying anvia-agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/anvia-hq-anvia-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/anvia-agent
What's inside
- Skill name
anvia-agent- Description
- Build Anvia agents and tools — Agent options, tool definitions, approvals, memory, streaming, multi-agent teams, and provider wiring.
- License
- MIT
- Instructions
- 60 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- agent-options.md · references/
- providers.md · references/
- teams.md · references/
- tools.md · references/
- check-agent.sh · scripts/
SKILL.md (first lines)
# Anvia Agent Skill
Use this skill when the user wants to build or change an Anvia agent: defining
tools, configuring the `Agent`, handling approvals and streaming, adding memory,
composing specialists, or wiring a provider model.
For work that must survive process restarts, use the `anvia-durable` skill for runtime
submission, owned subagents, and recovery policies. Ordinary streaming, teams, and memory
do not provide durable execution checkpoints.
## Process
1. Define tools first (`references/tools.md`) — zod schemas, approvals.
2. Create the `Agent` (`references/agent-options.md`) — smallest option set that works.
3. Wire the provider model (`references/providers.md`) — keep vendor SDKs in provider packages.
4. Compose specialists when needed (`references/teams.md`) — subagents as tools, or `AgentTeam`.
5. Run `scripts/check-agent.sh` from the app root before claiming done.
## Minimal slice
```ts
import { Agent } from "@anvia/core/agent";
import { createTool } from "@anvia/core/tool";
import { OpenAIClient } from "@anvia/openai";
import { z } from "zod";
const addTool = createTool({
name: "add",
description: "Add two numbers together.",
inputSchema: z.object({
x: z.number().describe("The first number."),
y: z.number().describe("The second number."),
}),
outputSchema: z.number(),
execute: (args) => args.x + args.y,
});
const client = new OpenAIClient({
baseUrl: process.env.OPENAI_BASEURL,
apiKey: process.env.OPENAI_API_KEY ?? "",
});
const agent = new Agent({
id: "agent",
model: client.completionModel({ modelId: "gpt-6-astra", api: "responses" }),
instructions: "You are a concise assistant. Use tools when useful.",
maxTurns: 2,
tools: [addTool],
});
const response = await agent.generate({ prompt: "What is 12 + 30? Use the add tool." });
if (response.type !== "response") throw new Error("Unexpected tool approval request.");
console.log(response.output);
```
## Output
Prefer one agent, few tools, explicit zod schemas. Point to the relevant
reference file instead of pasting its contents into chat.From anvia-hq/anvia, MIT.
More from anvia-hq/anvia
- 0.670score
anvia-durable
anvia-hq
Build recoverable Anvia workflows with @anvia/durable — durable main agents, owned subagents, task graphs, tool/effect recovery, persisted waits, and remote…
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-pipeline
anvia-hq
Build deterministic multi-step work with Anvia Pipelines — steps, composition, parallel branches, decision routing, batch runs, agent, extractor, and decision…
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-studio
anvia-hq
Run and inspect Anvia agents in Studio — local serving, playground, traces, approvals, sessions, evals, and observability.
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-evals
anvia-hq
Evaluate Anvia agents and retrieval — deterministic metrics, semantic similarity, LLM judges, RAG quality, and CLI eval runs.
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-channels
anvia-hq
Connect Discord, Slack, and Telegram to Anvia agents — channel adapters, agent-backed bots, proactive delivery, sessions, streaming, and platform actions.
SkillAFreshness: A★ 57Claude Code +9 - 0.664score
anvia-mcp
anvia-hq
Connect MCP servers to Anvia agents — clients, transports, tool discovery, URL safety, and lifecycle.
SkillAFreshness: A★ 57Claude Code +9 - 0.664score
anvia-chat
anvia-hq
Wire an Anvia chat UI end to end — server stream route, client transport, React hook, and UI primitives.
SkillAFreshness: A★ 57Claude Code +9 - 0.664score
anvia-rag
anvia-hq
Build retrieval and RAG with Anvia — chunking, embeddings, vector stores, knowledge graphs, filters, and search tools.
SkillAFreshness: A★ 57Claude Code +9 - 0.659score
release-notes
anvia-hq
Draft concise product release notes from a list of shipped changes.
SkillAFreshness: A★ 57Claude Code +9
Signals
- Stars
- 57
- Forks
- 6
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (21 days ago)
- Last release
- Oct 23, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/anvia-hq/anvia
- Website
- anvia.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from anvia-hq
- 0.670score
anvia-durable
anvia-hq
Build recoverable Anvia workflows with @anvia/durable — durable main agents, owned subagents, task graphs, tool/effect recovery, persisted waits, and remote…
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-pipeline
anvia-hq
Build deterministic multi-step work with Anvia Pipelines — steps, composition, parallel branches, decision routing, batch runs, agent, extractor, and decision…
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-studio
anvia-hq
Run and inspect Anvia agents in Studio — local serving, playground, traces, approvals, sessions, evals, and observability.
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-evals
anvia-hq
Evaluate Anvia agents and retrieval — deterministic metrics, semantic similarity, LLM judges, RAG quality, and CLI eval runs.
SkillAFreshness: A★ 57Claude Code +9 - 0.667score
anvia-channels
anvia-hq
Connect Discord, Slack, and Telegram to Anvia agents — channel adapters, agent-backed bots, proactive delivery, sessions, streaming, and platform actions.
SkillAFreshness: A★ 57Claude Code +9 - 0.664score
anvia-mcp
anvia-hq
Connect MCP servers to Anvia agents — clients, transports, tool discovery, URL safety, and lifecycle.
SkillAFreshness: A★ 57Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get anvia-agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
anvia-agent skill. Agent Mart. https://agentmart.dev/skills/anvia-hq-anvia-agent (last updated 2026-10-24)