@chanto/cli 0.1.4 → 0.1.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +36 -118
  2. package/package.json +6 -6
package/README.md CHANGED
@@ -6,7 +6,7 @@
6
6
 
7
7
  <p align="center">
8
8
  A fast, lean coding agent for your terminal.
9
- Any model, local or hosted, including your cloud's:
9
+ Local and cloud models, including:
10
10
  Amazon Bedrock, Google Vertex AI and Azure.
11
11
  </p>
12
12
 
@@ -14,22 +14,15 @@
14
14
  <img alt="Status: alpha" src="https://img.shields.io/badge/status-alpha-f59e0b">
15
15
  <a href="https://scorecard.dev/viewer/?uri=github.com/chanto-sh/chanto"><img alt="OpenSSF Scorecard" src="https://api.scorecard.dev/projects/github.com/chanto-sh/chanto/badge"></a>
16
16
  <a href="https://www.bestpractices.dev/projects/15833"><img alt="OpenSSF Best Practices" src="https://www.bestpractices.dev/projects/15833/badge"></a>
17
- <img alt="Rust" src="https://img.shields.io/badge/Rust-1.95%2B-000000?logo=rust&logoColor=white">
18
17
  <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue">
19
- <img alt="Local models" src="https://img.shields.io/badge/local-Ollama%20·%20llama.cpp%20·%20vLLM-10b981">
20
- <img alt="MCP" src="https://img.shields.io/badge/MCP-client%20%2B%20server-6C47FF">
21
- <img alt="Setup" src="https://img.shields.io/badge/setup-imports%20your%20existing%20config-6C47FF">
22
18
  <img alt="Platforms" src="https://img.shields.io/badge/platforms-macOS%20·%20Linux%20·%20Windows-0078D6">
23
19
  </p>
24
20
 
25
21
  > [!NOTE]
26
- > **Chanto is in alpha.** Expect rough edges and breaking changes before 1.0.
27
- > [Issues](https://github.com/chanto-sh/chanto/issues) and feedback are welcome.
28
- > It's built by one developer with a lot of help from AI coding agents; CI
29
- > runs the tests on Linux, macOS and Windows with code scanning, and the
30
- > [security model](docs/security-model.md) explains how it protects you.
31
-
32
- > Switching from another agent? Chanto reads the config you already have, so you don't start over.
22
+ > **Chanto is in alpha:** expect rough edges and breaking changes before 1.0.
23
+ > CI tests Linux, macOS and Windows. Read the [security model](docs/security-model.md)
24
+ > for the protections and their limits. [Issues](https://github.com/chanto-sh/chanto/issues)
25
+ > and feedback are welcome.
33
26
 
34
27
  <p align="center">
35
28
  <a href="docs/reference.md"><b>Docs</b></a> ·
@@ -42,32 +35,14 @@
42
35
 
43
36
  ## Install
44
37
 
45
- macOS and Linux:
46
-
47
- ```sh
48
- curl -fsSL https://chanto.sh/install.sh | sh
49
- ```
50
-
51
- Homebrew (macOS and Linux):
52
-
53
- ```sh
54
- brew install chanto-sh/tap/chanto
55
- ```
56
-
57
- npm, or Cargo (builds from source, needs Rust 1.95+):
58
-
59
38
  ```sh
60
- npm i -g @chanto/cli
61
- cargo install chanto --locked
39
+ curl -fsSL https://chanto.sh/install.sh | sh # macOS and Linux
40
+ brew install chanto-sh/tap/chanto # Homebrew
41
+ npm i -g @chanto/cli # npm
42
+ cargo install chanto --locked # from source (Rust 1.95+)
62
43
  ```
63
44
 
64
- Windows (PowerShell):
65
-
66
- ```powershell
67
- irm https://chanto.sh/install.ps1 | iex
68
- ```
69
-
70
- The installer checks the download's checksum and puts `chanto` in `~/.local/bin` (it tells you if that isn't on your `PATH`). Update later with `chanto upgrade`. To build from a checkout instead: `./install.sh --from-source` (needs Rust 1.95+).
45
+ On Windows (PowerShell): `irm https://chanto.sh/install.ps1 | iex`. The installers check the release signature and the download's checksum and put `chanto` in `~/.local/bin`; `chanto upgrade` updates it.
71
46
 
72
47
  ## First run
73
48
 
@@ -76,7 +51,9 @@ cd your-project
76
51
  chanto
77
52
  ```
78
53
 
79
- Chanto looks for what you already have: API keys in your environment, your Codex config, a running Ollama. Then it asks you to pick a model. No keys? Pick one of the free options: OpenRouter's free models, Gemini's free tier, or a model on your own machine. [Hosted models](docs/reference.md#hosted-models) covers every provider, including your ChatGPT plan, Amazon Bedrock, Google Vertex AI and Azure.
54
+ Chanto detects API keys, compatible configuration and local model servers, then asks you to pick a model. Use an API provider, your ChatGPT plan, or a local model through Ollama or an OpenAI-compatible server.
55
+
56
+ Run `chanto login chatgpt` for your ChatGPT plan. Subscription coding plans such as Kimi Code (`chanto login kimi-coding`) and Z.ai (`chanto login zai`) use their own plan keys. Login saves credentials; `/model` or `/models` selects the model. See [providers and login](docs/reference.md#hosted-models).
80
57
 
81
58
  Then just say what you want, like "fix the failing test in auth". Chanto asks before editing files or running risky commands, unless you allow them.
82
59
 
@@ -114,41 +91,17 @@ In a session:
114
91
 
115
92
  | | |
116
93
  |---|---|
117
- | **Fast and lean** | One native binary that starts instantly and stays light on CPU and memory while it works, with fewer tokens per task than most agents ([benchmarks](https://github.com/chanto-sh/benchmarks/blob/main/RESULTS.md)) |
118
- | **Any model** | Free to start (OpenRouter's free models, Gemini's free tier, or a local model); Ollama, llama.cpp, vLLM and other OpenAI-compatible servers; OpenAI, Anthropic, OpenRouter, DeepSeek and more; your ChatGPT login; Amazon Bedrock, Google Vertex AI and Azure with your cloud credentials |
119
- | **Safe by default** | Shell commands run in a sandbox on macOS and Linux (on Windows it confines writes only: reads and network aren't restricted), with optional network domain allowlists on macOS and Linux; risky actions need your OK, and auto mode screens commands for you |
120
- | **Undo** | `/rewind` restores files (including what shell commands changed) and the conversation to any earlier prompt |
121
- | **Outcome mode** | Agree on what "done" means first, then review results instead of code |
122
- | **Background runs** | `chanto run --bg "<task>"` (or `&task` in the TUI) works in its own git worktree and branch while you keep going; `chanto runs`, `attach` to answer prompts, `apply` to bring the result over; optional per-run Docker/Podman container for its commands (`[background] isolate = "docker"`, no network or an allowlist, CPU/memory limits) |
123
- | **Checks its work** | Runs the tests related to its change before saying it's done (the full suite when shared setup changed, or with `--verify-full`), tells failures it caused from ones that were already there, and won't weaken tests to pass |
124
- | **Finds its way in big repos** | `RepoMap` gives a ranked, token-budgeted map of the project's symbols; `SemanticSearch` finds code by meaning through `[embeddings]` (a local Ollama model by default). Both are read-only, so they run without a prompt |
125
- | **Plays well with others** | MCP, hooks, and Claude Code plugin marketplaces (`chanto plugin`) |
126
-
127
- <details>
128
- <summary><b>Everything else</b>: goals, teams, scheduled jobs, memory, voice and more</summary>
129
-
130
- | | |
131
- |---|---|
132
- | **Goals** | `/goal <objective>` keeps working across turns and context windows until the agreed, locked criteria pass; stops on limits or no progress, and asks when blocked |
133
- | **Teams** | `/team <task>` splits work into parallel sub-tasks in their own worktrees, reviews each one, merges them onto a team branch and runs your checks |
134
- | **Costs and diagnostics** | USD totals, session/daily budgets, a spend guard that estimates fan-out before it starts and explains costly loops, redacted daily logs, opt-in OTLP telemetry, `/feedback`, and opt-in error reports |
135
- | **Keeps secrets out** | Hides API keys and `.env` values from the model and logs |
136
- | **Durable memory** | Remembers user preferences and project facts across sessions, with visible saves and undo |
137
- | **Local models** | Tuned for small local models, and won't run your machine out of memory |
138
- | **Easy to install** | One-line installers that verify checksums, optional daily update notices, and `chanto upgrade` |
139
- | **Chanto cloud** | `chanto login cloud`, then models as `chanto/<model>` and agents that run on a schedule, on GitHub events or from CI: `chanto agents create`, `chanto agents run --wait`, `chanto cloud run --agent <name>` with `CHANTO_CLOUD_TOKEN` ([docs](docs/reference.md#chanto-cloud)) |
140
- | **Scheduled jobs** | `chanto runner`: cron, interval, webhook and CI triggers, each an isolated background run with budgets, verification and notifications |
141
- | **Drive another agent** | `chanto acp-client <command>` runs any ACP agent (Claude Code via `claude-agent-acp`, OpenCode, …) with Chanto's UI, permissions and your MCP servers; the agent can run commands through Chanto's terminals, its modes, settings and sign-in work through `/agent-mode`, `/agent-config` and `/agent-login`, and its own slash commands are passed through ([docs](docs/reference.md#driving-another-agent-acp-client)) |
142
- | **Learns from you** | Suggests lessons from your corrections, only applied when you approve |
143
- | **Customizable** | Ask `/customize` or `chanto customize` to add commands, skills, hooks and more; `/reload` applies extensions |
144
- | **Computer use** | Opt-in (`--computer`) desktop control beyond the browser: screenshots, clicks, typing and apps on macOS (built-in tools only) and Linux (X11, or Wayland with grim/GNOME/KDE screenshots and ydotool); every action needs your approval, and a status-line indicator shows it's on |
145
- | **Remote runs** | `chanto serve --runs` on your own server, then `chanto run --bg --on <server>`: the code goes as a git bundle or through your git remote, and the results come back the same way |
146
- | **Sessions** | Resume from any directory, fork current or past conversations, browse session trees, share redacted standalone HTML, and import sessions others share with you (`chanto import-session`) |
147
- | **Voice input** | ctrl+space or `/voice` in the TUI: dictate a prompt, transcribed locally with whisper.cpp (or a hosted endpoint you configure) and placed in the prompt for review ([docs](docs/reference.md#voice-input)) |
148
- | **Your terminal, your way** | A full-screen view, or `--inline` to print into your terminal's own scrollback (native scroll, search and copy); Markdown renders as it streams; `/effort` sets how hard the model thinks |
149
-
150
- Full list in the [docs](docs/reference.md).
151
- </details>
94
+ | **Local and cloud models** | OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter and more; ChatGPT and coding plans; Bedrock, Vertex AI and Azure; local OpenAI-compatible servers |
95
+ | **Permission controls** | Ask before risky actions, or use plan, accept-edits and auto modes. Shell sandboxing covers macOS and Linux; Windows restricts writes, with read/network limits described in the [security model](docs/security-model.md) |
96
+ | **Verification** | `--verify` adds a project-check gate before completion; `--verify-full` runs the full suite. The test-weakening guard also runs on ordinary turns ([reference](docs/reference.md#verified-mode-guardrails)) |
97
+ | **Sessions and undo** | Resume, fork and rewind conversations with file changes; share redacted transcripts |
98
+ | **Background work** | Run tasks in separate worktrees, monitor jobs, and apply their results while continuing your session |
99
+ | **Goals and teams** | Keep working toward agreed criteria or split a task across agents with checks and limits |
100
+ | **Extensions** | MCP tools, hooks, skills, custom commands and compatible plugin marketplaces |
101
+ | **Usage and costs** | Session token/cost totals, budgets, and provider-reported limits with low-quota warnings |
102
+
103
+ The [reference guide](docs/reference.md) also covers memory, scheduled jobs,
104
+ voice, remote runs, optional computer control and using another agent through ACP.
152
105
 
153
106
  <details>
154
107
  <summary><b>Compatibility: the existing Claude Code and Codex setup it reads</b></summary>
@@ -165,70 +118,35 @@ Project settings that could run code are ignored until you trust the folder.
165
118
 
166
119
  ---
167
120
 
168
- ## What's different
169
-
170
- Chanto is built around one rule: finishing means evidence, not a confident answer.
171
-
172
- - **A finish it has to earn.** Before accepting "done", Chanto runs the project's tests and sends failures back to the model. The final answer says what actually passed and how much of the suite that was.
173
- - **Tests are protected.** Existing tests are snapshotted each turn. Deleting them, weakening assertions or adding skips is caught and rejected: fix the code, not the test.
174
- - **Stopping is a feature.** Goals and teams keep working until agreed criteria pass, stop on limits or no progress, and ask when blocked instead of spinning.
175
- - **Local-first.** One Rust binary that talks to local or hosted models, reads existing agent config one way, and needs no account to start.
176
-
177
- ---
178
-
179
- ## How it works
180
-
181
- ```mermaid
182
- flowchart LR
183
- you(["You"]) --> agent["Agent"]
184
- agent <--> model["Model<br/><i>local or hosted</i>"]
185
- agent --> tools["Tools<br/><i>files · shell · web · MCP</i>"]
186
- agent --> check{{"Checks<br/><i>tests pass?</i>"}}
187
- check -->|no| agent
188
- check -->|yes| done(["Done"])
189
-
190
- classDef ok fill:#10b98118,stroke:#10b981;
191
- class check,done ok
192
- ```
193
-
194
- Every action goes through a permission check first, and secrets are masked before anything is sent to the model.
195
-
196
- ---
197
-
198
121
  ## Benchmarks
199
122
 
200
- Same model, same tasks and same rules for every agent. Tasks come from a public set, not ones written for Chanto.
123
+ Two things are measured, each with the same rules for every agent:
201
124
 
202
- The suite, every raw result and how to audit them live in [chanto-sh/benchmarks](https://github.com/chanto-sh/benchmarks).
203
- Results and caveats: [RESULTS.md](https://github.com/chanto-sh/benchmarks/blob/main/RESULTS.md).
125
+ - **Overhead:** the CPU time and memory an agent spends per turn on its own work, with the model taken out (a local mock answers instantly), every agent at a pinned version.
126
+ - **Task results:** pass rates on coding tasks from public sets (SWE-bench, HumanEval, DS-1000 and others) with the same model for every agent.
204
127
 
205
- ---
206
-
207
- ## Repository
128
+ Results, versions and caveats are in [RESULTS.md](https://github.com/chanto-sh/benchmarks/blob/main/RESULTS.md), with every raw result behind them. To check the overhead numbers on your own machine:
208
129
 
209
- ```
210
- src/ the agent (Rust)
211
- proto/ wire types shared by the CLI and the hosted service (chanto-proto)
212
- classifier/ auto mode's command classifier
213
- docs/ full reference
130
+ ```sh
131
+ git clone https://github.com/chanto-sh/benchmarks.git && cd benchmarks
132
+ python3 reproduce.py --quick # smaller selection; omit --quick for the full comparison
214
133
  ```
215
134
 
216
135
  ---
217
136
 
218
137
  ## Development
219
138
 
220
- Needs Rust 1.95 or newer (`rustup update stable`).
139
+ `src/` contains the agent, `proto/` shared wire types, and `docs/` the reference. Building requires Rust 1.95 or newer:
221
140
 
222
141
  ```sh
223
142
  cargo build # add --release for target/release/chanto
224
143
  cargo test
225
144
  ```
226
145
 
227
- Day-to-day commands and architecture notes are in [AGENTS.md](AGENTS.md); how to
228
- contribute, report a vulnerability, and behave are in [CONTRIBUTING.md](CONTRIBUTING.md),
229
- [SECURITY.md](SECURITY.md), and [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md). How the
230
- project is run and where it's going: [GOVERNANCE.md](GOVERNANCE.md) and
231
- [ROADMAP.md](ROADMAP.md); how Chanto defends you: [docs/security-model.md](docs/security-model.md).
146
+ [AGENTS.md](AGENTS.md) has the day-to-day commands and architecture; [CONTRIBUTING.md](CONTRIBUTING.md),
147
+ [SECURITY.md](SECURITY.md) and [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) cover contributing, reporting a
148
+ vulnerability and behaviour; [GOVERNANCE.md](GOVERNANCE.md) and [ROADMAP.md](ROADMAP.md) cover how the
149
+ project is run and where it's going.
232
150
 
233
151
  ---
234
152
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@chanto/cli",
3
- "version": "0.1.4",
3
+ "version": "0.1.6",
4
4
  "description": "A fast, lean coding agent for your terminal",
5
5
  "license": "Apache-2.0",
6
6
  "homepage": "https://chanto.sh",
@@ -19,10 +19,10 @@
19
19
  "node": ">=18"
20
20
  },
21
21
  "optionalDependencies": {
22
- "@chanto/cli-darwin-arm64": "0.1.4",
23
- "@chanto/cli-darwin-x64": "0.1.4",
24
- "@chanto/cli-linux-arm64": "0.1.4",
25
- "@chanto/cli-linux-x64": "0.1.4",
26
- "@chanto/cli-win32-x64": "0.1.4"
22
+ "@chanto/cli-darwin-arm64": "0.1.6",
23
+ "@chanto/cli-darwin-x64": "0.1.6",
24
+ "@chanto/cli-linux-arm64": "0.1.6",
25
+ "@chanto/cli-linux-x64": "0.1.6",
26
+ "@chanto/cli-win32-x64": "0.1.6"
27
27
  }
28
28
  }