Tokless
One CLI wires code analysis, context compression, and concise instructions into multiple coding agents.
- Source repo
- HoangP8/tokless
- Stars
- ★ 362
- Last updated
- today
- License
- MIT
- Primary language
- Go
- FA score
- 57/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer who alternates between Claude Code, Codex, and other supported clients and wants one place to maintain their shared tooling.
- Not a fit if
- Teams that need a fully offline install: the installer pipes a GitHub script into a shell
- Grok Build users who rely on RTK command rewriting
- Teams that cannot restart their agent sessions after install
- Source review
- 57/100 · Major gaps
What does this agent do, and when should you use it?
Tokless is a cross-platform installation and configuration CLI for coding agents on macOS, Linux, and Windows. It assembles karpathy-skills, caveman, ponytail, rtk, codegraph, and context-mode into a coordinated toolchain, then connects them through each client’s supported instructions, hooks, plugins, extensions, or MCP configuration. Documented clients include Claude Code, OpenCode, Codex, Antigravity, GitHub Copilot, Factory Droid, Pi, Cursor, Grok Build, Kilo Code, Oh My Pi, and Cline, although their integration methods and feature coverage differ. The installer detects supported agents already present on the machine and lets the user configure one, several, or all of them; the same CLI handles updates, diagnostics, disabling, and removal. Its deployment boundary is the user’s local agent configuration and per-project codegraph indexes—it does not provide a model, hosted coding service, or common chat interface.
Running tokless detects installed supported coding agents and wires in selected combinations of rtk, caveman, ponytail, codegraph, and context-mode. The documented instruction packages, including karpathy-skills, establish coding and response rules; rtk filters command output before it reaches the agent; codegraph indexes source relationships, call paths, and impact; and context-mode supplies sandboxed context operations, focused analysis, and session memory. Tokless writes the appropriate Instruction, Hook, Allow, Plugin, Extension, or MCP setup for each selected client. Its exposed MCP operations include codegraph_explore, ctx_execute, ctx_batch_execute, ctx_execute_file, ctx_index, ctx_search, and ctx_fetch_and_index. The tokless index command builds per-project codegraph indexes, tokless doctor reports what is wired and warns about broken pieces, and tokless update updates the CLI, shows version differences, and upgrades the installed tools.
- A developer who alternates between Claude Code, Codex, and other supported clients and wants one place to maintain their shared tooling.
- A team working in a large repository that wants indexed source relationships, call paths, and change-impact exploration.
- A terminal-heavy developer whose command output consumes too much agent context and needs filtering before the output reaches the agent.
- A frequent coding-agent user seeking focused context analysis, session memory, and reduced context-window consumption.
- A cautious adopter who wants to inspect intended configuration changes with --dry-run before any local writes occur.
- A team maintaining macOS, Linux, and Windows workstations that wants a consistent coding-agent toolchain across operating systems.
How do you install or deploy this agent?
On macOS or Linux:
curl -fsSL https://raw.githubusercontent.com/HoangP8/tokless/main/scripts/install.sh | bashOn Windows PowerShell:
irm https://raw.githubusercontent.com/HoangP8/tokless/main/scripts/install.ps1 | iexAfter installation, run tokless for interactive agent selection, or run tokless --agents claude,opencode to wire only those clients. The source does not specify a language runtime, administrator privileges, or required credentials. Installation requires network access to retrieve the GitHub-hosted script and associated tools. Restart configured agents afterward so they load the new configuration.
How do you use this agent?
For a first working invocation, run:
tokless
This installs the tools and prompts you to select detected agents; it is documented as safe to rerun. Use tokless --agents claude,opencode to restrict the target clients, or tokless --tools rtk,caveman,ponytail,codegraph,context-mode to select components. Add --dry-run to preview without writing, --verbose to show every step, or --yes to skip confirmations. Run tokless index to build per-project codegraph indexes, tokless doctor to inspect wiring and broken pieces, tokless info to display installation and configuration paths, and tokless update to update the CLI and tools. tokless disable disables selected agents, tokless uninstall removes everything Tokless touched, and tokless self-update updates only the CLI.
What are this agent's strengths and limitations?
- A single cross-platform CLI covers installation, updates, diagnostics, disabling, and removal across numerous coding-agent clients.
- It uses each client’s documented integration mechanisms—hooks, plugins, extensions, instructions, or MCP—instead of assuming one mechanism works everywhere.
- The bundled components have separated responsibilities: rtk filters output, codegraph maps code relationships, and context-mode handles focused context operations.
- --dry-run, --verbose, and tokless doctor provide concrete ways to preview changes and inspect the resulting setup.
- Users can select only the agents and tools they want rather than accepting the complete bundle.
- The documented installers pipe a GitHub-hosted script directly into Bash or PowerShell, so adopters must assess the remote script and its write scope before execution.
- Feature parity varies by client; Grok Build explicitly lacks RTK command rewriting.
- Agents must be restarted after installation to load the new configuration, interrupting active client sessions.
- The source does not document runtime versions, permission requirements, an offline installation path, or recovery behavior after network failures.
- The support table includes Kilo Code, but the documented --agents value list does not include kilo, leaving its CLI selection method unclear.
How does this agent compare with similar options?
Tokless does not replace karpathy-skills, caveman, ponytail, rtk, codegraph, or context-mode; it packages and connects those existing projects across coding-agent clients. Compared with installing and reconciling each component manually, it supplies one installation, update, diagnostic, and removal workflow. The tradeoff is that capabilities still depend on each client’s available hook, plugin, extension, and MCP mechanisms.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Tokless This agent | 57 · Major gaps | CLIFree | ★ 362 | today | Go | Codex · Claude Code |
| deepx-code | 53 · Major gaps | CLIFree + model costs | ★ 391 | 1mo ago | Go | OpenAI API |
| LeanCTX Context Intelligence | 69 · Some gaps | CLIFree + model costs | ★ 3.9k | today | Rust | Codex · Claude Code · OpenAI API · Claude API |
| Tura | 62 · Some gaps | CLIFree + model costs | ★ 664 | 1mo ago | Rust | — |
How does FollowAgents rate this agent?
Why each dimension lost points
The docs provide --dry-run, harness/tool scoping, interactive harness selection, preservation of foreign configuration, and refusal to overwrite a managed setting after user edits. They describe the local Headroom proxy path and handling of OAuth/BYOK settings, supporting limited scope and some recovery. Deductions: installer examples pipe remote scripts into curl/irm execution, proxy autostart is on by default, and Linux enable-linger is retained. The packet does not explain key storage, transport protections, or permission isolation in detail. Dependency security evidence is thin: CI attempts an @latest install and ignores failure with || true.
README, installation notes, and CLI help are broadly aligned; invalid values produce allowed-value or usage errors, and doctor is documented to report health and warnings. Deductions: the README lists 16 harnesses while the CLI lists 17, and the CI workflow ignores failure to install external tools; dependency pinning and availability behavior are not established by this packet.
The project targets multiple coding harnesses, names macOS, Linux, and Windows, and offers harness/tool selection, proxy configuration, an offline-related CLI flag, and configuration paths for supported environments. Deductions: despite claims of any OS, 30-second setup, and zero configuration, the packet does not establish every harness's compatibility boundaries or an offline installation path; proxy and autostart defaults may vary in effect by environment.
The README is organized around installation, tools, configuration, usage, and per-harness paths. Installation notes include steps, commands, preview, health checks, and proxy rollback guidance; the provided license is MIT. Deductions: the README and CLI disagree on harness count, version history and changelog evidence are limited in the packet, and maintenance responsibility is not explicitly stated beyond repository/workflow clues.
The CLI integrates rules, command-output compression, code indexing, context tools, and project memory, and claims to trim MCP exposure from 27 tools to 10. Commands and management entry points are concrete. Deductions: benefits such as compression, indexing, persistent memory, and token savings are primarily asserted without outcome data or independent corroboration; runtime and integration costs are not quantified.
Many product claims are tied to named tools, ports, configuration paths, commands, and proxy behavior; CI files describe build and test workflows. Deductions: the packet contains no test results or item-by-item corroboration of README compatibility claims, CI tolerates some external dependency installation failures, and promotional benefit claims are not clearly separated from demonstrated facts.
- The documented installers execute scripts fetched from remote URLs; review the scripts and use --dry-run to inspect intended writes before configuration.
- Headroom autostarts by default, and the docs say Linux retains enable-linger. Review the proxy and login-start behavior before enabling it.
- The README and CLI differ on harness count; check the CLI's accepted IDs and doctor output.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/tokless)<a href="https://followagents.com/en/agents/tokless"><img src="https://followagents.com/badge/tokless.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's Changed * chore: readme badge colors by @HoangP8 in https://github.com/HoangP8/tokless/pull/59 * fix: Defender false-positive handling and rollback (#60) by @HoangP8 in https://github.com/HoangP8/tokless/pull/61 Full Changelog: https://github.com/HoangP8/tokless/compare/v1.0.11...v1.0.12View on GitHub ↗ -
Release notes excerpt
What's Changed * fix(context-mode): support context-mode 2.x (#56) by @HoangP8 in https://github.com/HoangP8/tokless/pull/58 Full Changelog: https://github.com/HoangP8/tokless/compare/v1.0.10...v1.0.11View on GitHub ↗ -
Release notes excerpt
Full Changelog: https://github.com/HoangP8/tokless/compare/v1.0.9...v1.0.10View on GitHub ↗
FAQ
Does Tokless require API keys or a paid model subscription?
What does the installer modify?
Can I install it for only one agent or a subset of tools?
What should I do if the integration becomes unhealthy?
Do all supported clients receive identical capabilities?
Thanks — we use this to improve the page.