Risky 52Coding & Developmentšuniversal
AgenC Core
Private AgenC core runtime repository
Quick Start
Install this Skill
npx skills add tetsuo-ai/agenc-core# AgenC Core > Daemon-backed coding agent: interactive TUI, headless print mode, background > agents, multi-channel gateway, budget-bounded autonomy, and a typed embedding SDK.     **AgenC Core** is the implementation repository for the `agenc` CLI. A local daemon owns agent/session lifecycle, permissions, provider calls, and command execution. The interactive TUI, headless `--print` / `--no-tui` CLI, background agents, channel gateway, and remote phone bridge are all clients of that daemon. | Package | Path | Role | | --- | --- | --- | | `@tetsuo-ai/agenc` `0.17.0` | `packages/agenc/` | Public launcher binary | | `@tetsuo-ai/runtime` `0.17.0` | `runtime/` | Daemon, TUI, tools, providers, tests | | `@tetsuo-ai/agenc-sdk` `0.3.0` | `packages/agenc-sdk/` | Typed embedding SDK (daemon protocol) | Documentation map: [`docs/INDEX.md`](docs/INDEX.md). Architecture: [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md). CLI reference: [`docs/reference/cli.md`](docs/reference/cli.md). ## Contents - [Features](#features) - [Project status](#project-status) - [Requirements](#requirements) - [Quick start](#quick-start) - [Usage](#usage) - [Configuration](#configuration) - [Architecture](#architecture) - [Development](#development) - [Security](#security) - [Contributing](#contributing) - [License](#license) ## Features - **Daemon-backed process model** ā launcher ā daemon (`app-server`) ā TUI / print / agents / gateway clients. One control plane per `AGENC_HOME`. - **Two front-ends** ā interactive React TUI and headless one-shot mode (`agenc -p|--print`, `agenc --no-tui`). - **Background agents** ā fire-and-forget sessions (`agenc agent start|list| attach|stop|logs`), attachable and resumable, independent of the foreground UI. - **Channel gateway** ā Telegram, Discord, Slack, WebChat, and stdio channels; pairing, bindings, in-channel approvals. See [`docs/gateway.md`](docs/gateway.md). - **Budget-bounded execution** ā daemon-owned reservations, hierarchical caps, concurrency, cancellation, and evidence across interactive/background work, including heartbeat / cron / hooks. Design: [`docs/design/execution-admission-kernel.md`](docs/design/execution-admission-kernel.md). - **Guided onboarding** ā `agenc onboard` includes AgenC account sign-in, X / xAI sign-in for Grok, provider API keys, and local providers without requiring slash commands; follow-on acts: `identity`, `channel`, `autonomy`, `recap` (personas, channels, budget/heartbeat/webhooks). - **Remote control** ā pair iOS or Android with `agenc remote on|off|status`; co-drive chats, receive background completion/attention events, and settle permissions from the phone. Android can route an explicit, physically approved `@ledger` SOL transfer to a Ledger Flex. See [`docs/remote-control.md`](docs/remote-control.md) and the [Ledger security contract](docs/security/mobile-ledger-transfer.md). - **Ledger Wallet CLI** ā Ledger hardware-wallet requests route through a bundled skill and a read-only CLI status tool. If the official `wallet-cli` is missing, AgenC asks before downloading anything; an approved `/ledger install` (or agent install action) resolves `@ledgerhq/wallet-cli@latest`, verifies the platform package's SHA-512 integrity, and installs it under `AGENC_HOME`. - **Built-in tools** ā Bash, file read/write/edit, transactional `apply_patch`, web fetch/search, LSP, MCP, sub-agents; read-before-write and atomic-patch safety. - **Browser automation** ā the `Browser` tool drives an isolated Chromium over a CDP pipe with stable accessibility refs (navigate, snapshot, click, type, screenshot, tabs). All eg ⦠(truncated)
Repository
41stars
12forks
Details
DiscoveredSep 4, 2026
Last UpdatedOct 17, 2026
Author@tetsuo-ai
Quality Score
45/100
Security52/100
- Dangerous shell command
- No license found
Related Skills
More coding & development skills you might like
Reticle
RiskyCoding & Development
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
š¤claudešuniversal
1.2k
190
View
agentscope-java
SafeCoding & Development
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
šuniversal
6.0k
1.5k
View
misakanet-failure-memory
SafeCoding & Development
š A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
š¤claudeāØļøcursoršuniversal
424
158
View
ospec
SafeCoding & Development
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
āØgeminiš¤claudeš¬gptšuniversal
396
28
View