Skip to main content
     ██╗  █████╗  ██████╗  ███╗   ██╗
     ██║ ██╔══██╗ ██╔══██╗ ████╗  ██║
     ██║ ███████║ ██████╔╝ ██╔██╗ ██║
██   ██║ ██╔══██║ ██╔══██╗ ██║╚██╗██║
╚█████╔╝ ██║  ██║ ██║  ██║ ██║ ╚████║
 ╚════╝  ╚═╝  ╚═╝ ╚═╝  ╚═╝ ╚═╝  ╚═══╝

J.A.R.N. — Just A Reliable Nerd

A TUI-first coding agent harness built on DeepAgents.

English · ภาษาไทย


J.A.R.N. is a terminal coding agent in the spirit of Claude Code and Codex CLI, but built as its own opinionated harness on top of the DeepAgents library. Its defining trait is reliability: it plans before acting, can enforce project verification, and asks before doing anything risky. With verify.gate: auto, a failed acceptance command triggers one bounded repair attempt and blocks successful completion if it still fails.

It runs entirely in your terminal (a Web UI is on the roadmap, post-launch). Notable capabilities: AGENTS.md / CLAUDE.md interop (works out-of-the-box beside other agents), headless one-shot mode (jarn -p "..."), JSONL session transcripts, ! shell escape (output fed into the next agent turn as context), OS-level execution sandbox (macOS sandbox-exec / Linux bwrap) and Docker container backend (execution.backend: docker), presets (/preset, jarn --preset) that set mode + sandbox at once, with an untrusted floor, auto-checkpoint + /undo / /redo, repo map (/map), a wiki knowledge base (/wiki), /config settings panel (interactive tabbed UI, persists to ~/.jarn/config.yaml), and per-server MCP health (/mcp status).

Status: this source line targets v1.0.10 General Availability. Publication is controlled by automated gates, protected UAT, and strict evidence; consult the GitHub Releases, PyPI, and npm pages for the currently published version. v0.10 adds an optional single-operator Telegram gateway: long-poll DM control, isolated per-root workers, durable approval cards, inbound media, scheduling, and VPS/systemd deployment. Earlier releases landed engine reliability; UX parity with Claude Code (live in-place streaming, /theme, @git:/@url: mentions, word-level diffs, ghost autosuggest, conversation /rewind with file restore); differentiators (--add-dir multi-root, inline images, headless --output-schema, labelled subagent streaming, pluggable web search, an LSP-lite diagnostics loop, a verified-completion badge); and launch systems (a reusable GitHub Action + a nightly eval harness). The architecture, configuration, permission engine, and terminal REPL are implemented and tested; live model calls require your own API key. See CHANGELOG.md and SECURITY.md.

Security: J.A.R.N. runs tools on your host by default (real filesystem + shell). A project's .jarn/config.yaml can declare hooks, MCP servers, and provider overrides — only trust repositories you would run code from. Untrusted projects are gated until you approve (jarn trust). Read SECURITY.md before use.

Why J.A.R.N.?

  • Reliable without prompt micromanagement — a small outcome-and-safety kernel leaves the model free to adapt its workflow to the task. The default verify.gate: suggest shows the detected acceptance command; opt-in verify.gate: auto runs it before completion. The completion badge — ⎿ verified: pytest ✓ 214 passed · 3.2s — confirms the result. A failure is fed back for a bounded repair round and, if still failing, ends the turn/headless run as an error instead of success. A diagnostics feedback loop (LSP-lite) then lints/type-checks just the files each turn edited (ruff + pyright) and can queue one bounded auto-fix round, so the agent catches the type error it just introduced (verify.diagnostics: auto).
  • Safe by default — a multi-layer permission system (coarse modes + fine-grained rules) sits in front of every file write and shell command, backed by a hard danger-guard that always confirms catastrophic actions — even in YOLO mode.
  • Instruction-aware — project context and skills guide only the user's stated goal. Source files, web pages, logs, and tool results are treated as data, so embedded instructions cannot override user intent or the harness's permission, trust, and sandbox boundaries. The agent uses only tools exposed by the active policy and backend.
  • Bring your own model — 14 providers, including Codex through your ChatGPT subscription, OpenRouter, Anthropic, OpenAI, Google, Mistral, Groq, DeepSeek, Together, Fireworks, xAI, Ollama, LM Studio, and a generic OpenAI-compatible endpoint, with per-task routing so subagents can use cheaper models.
  • Labelled subagent streaming — output from delegated task subagents is tagged with a dim ┊ <name> prefix and collapses to a single └ <name>: working… (N tool calls) status line (full text in the Ctrl+O pager), so parallel subagents no longer interleave anonymously.
  • Cost- & context-aware — live token/cost tracking (with a per-tool breakdown) and a per-session budget that can warn or hard-stop; a context-% gauge and live generation throughput (tok/s) that work for local models (LM Studio / Ollama) too, not just priced cloud ones.
  • Observable prompt modules — only the 146-word reliability/safety kernel is unconditional. Plan guidance, trusted project context, memory/skill/wiki catalogs, repo maps, the date, and explicitly loaded skill bodies are activated when relevant, budget-capped, and manageable through an interactive /modules picker with short explanations. /modules active retains the detailed scope, source, token, and truncation report.
  • Date-aware — the current local date is injected once per thread/day, so "today"-relative requests don't anchor to the model's training cutoff.
  • Pluggable web search — web_search supports Tavily, Brave Search, and Exa in addition to the keyless DuckDuckGo fallback. Set search.provider: auto (default) and export TAVILY_API_KEY / BRAVE_API_KEY / EXA_API_KEY — the first one set wins.
  • Extensible — skills, slash commands, custom subagents, lifecycle hooks, and MCP servers, all configured through plain files in ~/.jarn and .jarn/.

Install

macOS (Apple Silicon) and Linux (x64 / arm64) are supported; on Windows use WSL.

Recommended — one-command installer:

jarn_installer_tmp=$(mktemp "${TMPDIR:-/tmp}/jarn-install.XXXXXX") && trap '[ -z "${jarn_installer_tmp:-}" ] || rm -f "$jarn_installer_tmp"' 0 HUP INT TERM && curl -fsSL 'https://raw.githubusercontent.com/chayapats/jarn/main/install.sh' -o "$jarn_installer_tmp" && sh "$jarn_installer_tmp"; jarn_install_rc=$?; [ -z "${jarn_installer_tmp:-}" ] || rm -f "$jarn_installer_tmp"; trap - 0 HUP INT TERM; if [ "$jarn_install_rc" -eq 0 ] || [ "$jarn_install_rc" -eq 10 ]; then exec "$SHELL" -l; else (exit "$jarn_install_rc"); fi

The command first downloads the installer to a private temporary file, so a failed download is never executed. The installer inventories old jarn commands, detects the OS/CPU/libc, verifies the release checksum, stages and smoke-tests the candidate, activates it transactionally, and verifies what a fresh shell resolves. If a native binary cannot run (for example because of older GLIBC), it uses an isolated managed Python fallback. The final exec solves the parent-shell PATH limitation; status 10 means installation is verified but shell activation was still required, and status 20 means setup remains incomplete.

The installer can acquire a compatible official standalone Codex dependency during ChatGPT setup after showing its source, version, purpose, destination, and integrity checks. No separate Node/npm/Python/Codex preparation is required on the standard path. See the five-minute quickstart.

Advanced installation alternatives

Via npm — a self-contained binary, no Python required:

npm install -g jarn-cli     # installs the `jarn` command (also available as `jarn-cli`)

Intel macs install via pip/uv instead (no npm binary is published for them).

Via pip / uv — requires Python 3.12+ and uv:

pip install jarn            # PyPI (alpha)
# or: uv tool install jarn

From source:

git clone https://github.com/chayapats/jarn && cd jarn
uv sync --extra dev --extra telegram
uv run jarn

uv.lock is tracked in the repo so every teammate gets the same dependency versions.

Package-manager installs retain package-manager ownership; use that manager to update/remove them unless J.A.R.N. presents and you confirm an explicit migration.

Sharing with your team

git clone <repo-url> && cd jarn
uv sync --extra dev --extra telegram
uv run jarn setup          # once per machine — stores only a keychain/env/file reference in config
cd your-project
jarn doctor                # config, providers, and loaded extensions
jarn                       # trust prompt appears if the project declares hooks/MCP
jarn trust .               # pre-approve a repo you control (optional)

If a cloned project ships .jarn/config.yaml with hooks, MCP servers, or provider overrides, J.A.R.N. asks before honouring them. Decline to run safely with those settings stripped, or run jarn trust <path> after reviewing the repo. Use jarn doctor to see which skills, commands, subagents, hooks, and MCP servers would load (including shadowed or skipped files).

Uninstall

Removal is itemized and preserves user data by default:

jarn uninstall                         # choose categories interactively
jarn uninstall --yes                   # remove only the managed executable
jarn uninstall --sessions --cache      # confirm only those two categories
jarn uninstall --credentials --yes     # explicitly remove J.A.R.N. credentials

Categories are executable, exclusively owned dependencies, configuration, sessions, cache/logs/telemetry, and credentials. Shared Node, Python, uv, and Codex installs are never removed. Project-local .jarn/ directories are never touched. See Update, rollback, and uninstall.

Quick start

With a ChatGPT/Codex subscription (no OpenAI API key billing):

jarn setup                # choose “Continue with ChatGPT”
# Setup offers a verified Codex dependency install when needed, then shows login.
jarn auth status          # verifies dependency, auth mode, plan/workspace
cd your-project && jarn

J.A.R.N. talks to the official local Codex App Server; it never reads or stores ChatGPT OAuth tokens. Codex's own execution surfaces are disabled in this provider, and requested tools are translated back into ordinary J.A.R.N. tool calls so the existing permission, danger-guard, checkpoint, and /undo paths remain authoritative. Subscription usage is shown as tokens with $0 API cost and still consumes the limits/credits of your ChatGPT plan. For shared CI, use an API-key provider instead.

With OpenRouter OAuth (separate, advanced credential command):

jarn login        # opens browser → authorize → key stored in OS keychain
cd your-project
jarn              # launch the TUI (runs setup if still needed)

Or configure manually:

jarn setup        # first-run wizard: pick a provider, store your API key, choose defaults
cd your-project
jarn init         # create a JARN.md project-context file (optional but recommended)
jarn              # launch the TUI
jarn doctor       # diagnose config / providers / keys / extensions at any time
jarn bug          # write a privacy-scanned report; ask before opening GitHub

Shell completions (tab-complete subcommands and flags):

# zsh — run once, then restart your shell
jarn completions zsh > ~/.zfunc/_jarn
# add to ~/.zshrc if not already: fpath=(~/.zfunc $fpath) && autoload -Uz compinit && compinit

# bash — run once, then source or restart
jarn completions bash > ~/.bash_completions/jarn.bash
# add to ~/.bashrc: source ~/.bash_completions/jarn.bash

# fish — run once
jarn completions fish > ~/.config/fish/completions/jarn.fish

On first launch with no config, J.A.R.N. runs the setup wizard automatically. Transactional setup accepts an environment reference or an in-memory pasted key; it deliberately does not run OpenRouter OAuth because that exchange persists a key before final confirmation. Run jarn login separately when OAuth is desired.

Telegram gateway (optional)

v0.10 adds a single-operator, DM-only gateway for an always-on VPS. The npm binary includes it; Python installs need the optional extra:

pip install 'jarn[telegram]'       # omit for the standalone/npm distribution
jarn gateway setup

The wizard verifies the token with Telegram, asks you to send /start to the bot, discovers and confirms your numeric user ID, stores the token in the OS keychain (owner-only file fallback), updates the global config transactionally, and on Linux offers an owner-scoped systemd service. No token or hand-edited YAML is required. Use jarn gateway status afterward. Advanced repo allowlisting and manual service deployment remain documented in the Telegram gateway guide; never put gateway: in a project's .jarn/config.yaml.

Non-interactive / scripting

jarn exec "summarise the open TODOs"        # recommended discoverable form
jarn exec --json "what changed?"            # one machine-readable JSON result
jarn -p "summarise the open TODOs"          # one-shot: print reply and exit
echo "what changed?" | jarn -p -            # read prompt from stdin
jarn -p "do X" --json                        # emit JSON: {result, tokens, cost, turns}
jarn -p "do X" --model anthropic/claude-opus-4-8  # override model for this run
jarn -p "do X" --permission-mode auto-edit  # allow file writes without prompting
jarn -p "do X" --cwd /path/to/project       # set working directory
jarn -p "extract the version" --output-schema schema.json --json  # structured output

jarn exec and the shorter legacy jarn -p spelling use the same execution, permission, output, and exit-code contract.

Structured output (--output-schema): pass a JSON Schema file to constrain the agent's final answer. The parsed object replaces the free-text result field in the --json envelope, making CI parsing trivial:

jarn -p "list changed files as JSON" --output-schema files.schema.json --json \
  | jq '.result.files[]'

Exit codes when --output-schema is used: 0 success (structured object in result); 9 with error.kind: "schema" if the agent fails to produce a conforming response; 2 with error.kind: "usage" if the schema file can't be read or parsed.

Fail-closed safety: the default modes (ask / plan) refuse any tool that would normally prompt for approval and exit non-zero. Pass --permission-mode auto-edit or yolo to allow unattended tool use — the danger-guard still blocks catastrophic commands in every mode.

In CI

J.A.R.N. ships a GitHub Actions composite action so you can run it in any workflow — PR review, issue-fix bots, nightly audits.

- uses: chayapats/jarn/action@main
  with:
    prompt: "Review this diff: …"
    preset: "review-only"     # read-only; use 'ci' for write-enabled runs
    max_turns: "5"
    api_key: ${{ secrets.OPENROUTER_API_KEY }}

Outputs: result, cost_usd, turns.

Docker note: the default ci preset requires Docker (ubuntu runners have it). For docker-less runners (macOS/Windows) use preset: trusted-repo with permission_mode: auto-edit — see docs/GITHUB_ACTION.md.

Example workflows: PR review bot · Issue-fix bot. Full docs: docs/GITHUB_ACTION.md.

The interface: native inline

jarn            # start a session
jarn --resume   # pick a previous session to resume on launch
jarn --add-dir ../shared-lib --add-dir ../sibling-repo  # extra writable roots (repeatable)

Multi-root workspaces (--add-dir): by default the agent's write scope is the project root. Pass --add-dir <dir> (repeatable) to grant scoped write access to a sibling directory too — useful for monorepo/sibling-repo work. Each dir must exist and be a directory. The launch flag works for headless runs too (`jarn -p … --add-dir

`). You can also add one mid-session with `/add-dir

Metadata

Release files for jarn 1.0.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jarn 1.0.10
File Size Uploaded Provenance Actions
jarn-1.0.10.tar.gz 1.3 MB With provenance Details for jarn-1.0.10.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for jarn 1.0.10
File Interpreter ABI Platform Actions
jarn-1.0.10-py3-none-any.whl Python 3 none any Details for jarn-1.0.10-py3-none-any.whl

Total release size: 2.2 MB

Release files / jarn-1.0.10.tar.gz

Download URL jarn-1.0.10.tar.gz
Size 1.3 MB
Tags Source
SHA-256 checksum
How to use checksums
1842e6de58a9d9f4bbd49a109dd7408e4027d870dc91e2043eda73fb99d692dd
BLAKE2b-256 checksum
How to use checksums
e410005c7b1306670fff1564cc972e740c03cd7aa7498270f7f33b7f21790760
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 21, 2026.

Transparency log

Release files / jarn-1.0.10-py3-none-any.whl

Download URL jarn-1.0.10-py3-none-any.whl
Size 882.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c34a950a0bab10d59a9ce943d557a11fb8dc8812d1dbc7b52e6163b84c263e6a
BLAKE2b-256 checksum
How to use checksums
38c778fc8dd33ea20c9e9ed29959135a104b366da374796ce5f20bb88292ffed
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 21, 2026.

Transparency log

Security for jarn 1.0.10

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for jarn-1.0.10.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 21, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page