coder

package
v0.7.4 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Nov 2, 2026 License: MIT, MIT Imports: 5 Imported by: 0

README

The Coding agent

The Coding agent is a persistent agent for software work: it writes, builds and runs code, keeps its projects and its conversation between starts, and deploys to a dev server you give it. It runs on your computer: you start it, talk to it, stop it, and when you start it again the conversation continues.

It builds and runs software, reaches the internet and reads what you put in its share folder as it is. That is riskier than an agent that only reads and writes: give it a share folder and a dev server of their own.

This is the package that runs

The Coding agent is built into the Agentry CLI and the desktop app, and it runs from there: agentry agent enable coder, agentry agent start coder, then agentry agent chat coder, in the CLI. This release has the same bytes. The registry built its archive from the package the CLI carries, and the archive's digest is the one the CLI reports. Run agentry builtins to print it and compare it with the digest on this page.

Installing this release does not give you a second Coding agent: the CLI refuses to install a built-in's release as a persistent agent, and runs the one it carries. It never runs this release as an ordinary QuickAgent, since the release declares only the persistent mode.

What the application gives it

The manifest declares no network access, no file access, no commands and no run secret. Under capabilities.persistent it declares skills (skills), the stored secret it asks for (secrets: BRAVE_API_KEY; you may store others) and the coding toolchain (coder: any program in its toolchain image, open egress, a public browser, a dev server, ports and git host accounts, each a switch you agree to). When the application runs the Coding agent, it gives it what follows. agentry agent show coder lists what it has, and its first start asks you to agree to each part:

  • Programs. run_command runs any program in its toolchain image (agentry-coder: GCC, Make, CMake, pkg-config, Git, curl, Python 3 with pip and venv, Go and Node with npm, the git hosts' CLIs gh, glab and tea, and the scanners osv-scanner and gitleaks), in a folder of its own, as you. A program can write only in its folders and its temporary folder, and its output is capped. One it runs in the foreground has a time limit; one it starts in the background, such as a dev server, has none and keeps running until it stops it or the segment ends, at most four at a time. No program list applies: this is what lets it build software.
  • Open egress. Its tools and the programs it runs reach any address on the internet: package registries, repositories and any site. The model itself is reached only through the runner's model proxy, as for every run.
  • A browser on any public website, through the runner's browse proxy.
  • A dev server, when you give it one (agentry agent configure coder --dev-host user@host): reached over SSH through the runner's host link, as the account you sign in with, its host key pinned and its sign-in kept in your system keychain.
  • Ports, when you add them (agentry agent configure coder --port web=3000): what it serves on that port inside its sandbox opens on your computer at http://127.0.0.1:3000, while the port and its programs are on. Only you add a port.
  • Its folders. Its own data volume, where it keeps its projects and notes, kept until you reset it, and a share folder of yours, ~/agentry/codingshare unless you choose another, mounted read and write. What you put in the share is read as it is, with no malware check.
  • Skills. Folders of instructions it reads, read-only, in skills/: four built in (review a change, test first, audit dependencies, open a pull request), and any you add from a folder or a .zip on your computer (agentry agent skill add coder <path>). A skill you add is your own: Agentry has not reviewed it, and its scripts run with the agent's programs. Each skill is an entry of its roster.
  • Git host accounts, when you give it one (agentry agent configure coder --account github.com --own …): an account on GitHub, GitLab, a Gitea, Forgejo or Codeberg host, or any other git host. Give it an account of its own and share repositories with it: it then reaches only what you share, its commits and pull requests are its own, and taking access away is removing a collaborator. Your own account lets it do whatever the token can. The token stays in your system keychain; its programs sign in with it (Git over https to that host alone, and gh, glab or tea) and can read it, and it commits there as the name and email you give.
  • Stored secrets, when you store them (agentry agent secret set coder NAME): each in its programs' environment by its name, its value in your system keychain. Its programs can read it and send it anywhere they reach.
  • A dependency scan: dependency_scan runs OSV-Scanner from its toolchain image, offline, over a project's lockfiles and manifests, against OSV's vulnerability databases, which Agentry downloads to your computer once a day (about 300 MB) and gives it read-only. It never asks OSV's service, and a database it does not have is an error, never "no vulnerabilities". It is an entry of its roster, on while its programs are.
  • MCP servers it comes with, each an entry of its roster that you switch on and off: library documentation from Context7 (@upstash/context7-mcp), on until you switch it off; GitHub's own server, read-only unless you also switch on its changes, and GitLab's, for gitlab.com or the self-managed GitLab you give it an account on (from GitLab 19.2, once its administrator allows MCP access), each off until you give it an account on that host, whose token signs it in; and web search with Brave, off until you store your own Brave Search API key for it. Each reaches only its provider's host. It also suggests a server you can add as your own: code scanning with Semgrep (the semgrep package's semgrep mcp), which reaches only semgrep.dev and is sent the code the agent passes to its tools, never its projects. Agentry ships no Semgrep rules, and Semgrep's terms apply (agentry agent configure coder --add-suggested semgrep).
  • What you add: knowledge packs from your computer and MCP servers.

Each part is an entry of its roster that you can switch off, and switching one on that you have not agreed to on this computer asks you first. Each start is a segment with its own receipts, which record what it had. It runs without the session caps an interactive QuickAgent has, on the harness and model your runner policy names, in a container.

Using Agentry: https://docs.secureagentry.net/

Documentation

Overview

Package coder is the Coding agent: the built-in persistent agent for software work, embedded in the CLI. Its manifest declares the persistent run mode alone, no egress, no filesystem, no exec and no secret; what the application gives it (its programs, open egress, a browser, a dev server) is listed in its README.

Index

Constants

View Source
const (
	Namespace = "agentry"
	Name      = "coder"
	Version   = "1.5.0"
)

The package's identity, as its manifest declares it.

Variables

This section is empty.

Functions

func FS

func FS() fs.FS

FS is the package's tree: agent.yaml, INSTRUCTION.md, README.md and LICENSE at its root, and its skills, one folder each beneath skills/.

func OfferedServers added in v0.6.999

func OfferedServers(hosts []offer.GitHost) []offer.Server

OfferedServers are the MCP servers the agent comes with, each an entry of its roster: library documentation on by default, and the git hosts' servers and web search off until it has an account or a key. An account on a self-managed GitLab adds GitLab's server at that host's address; a host on a port other than 443 has none, since a remote server is reached on 443 alone.

func SuggestedServers added in v0.6.999

func SuggestedServers() []offer.Suggestion

SuggestedServers are the MCP servers the agent suggests, which the person adds as their own: Semgrep, whose rules Agentry may not ship, so it runs under the person's own use of Semgrep's terms. It is a subcommand of the semgrep package's CLI and reaches semgrep.dev alone, its metrics and its OpenTelemetry export switched off (their hosts are refused either way). It joins a network, so it is never given the agent's projects, and it is given only the tools that work on code passed in the call: a scan with a rule the agent writes, the languages, and a syntax tree. Its plain scan and supply-chain scan read files from disk, its rule schema is fetched from a host it does not reach, and its findings need a Semgrep account.

Types

This section is empty.

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL