Kilo Code (15K+ GitHub stars, 98 HN points) is an all-in-one agentic
engineering platform with native OpenRouter support. Adds agent entry,
sprite implementation, and missing matrix entries for all 21 clouds.
Agent: team-lead
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
printf %q escapes spaces and shell metacharacters, turning "claude install"
into "claude\ install" — which bash -c interprets as a single command named
"claude install" (with literal space). This broke all multi-word commands
passed to run_sprite, including pipes, redirects, and && chains.
Since all callers pass trusted, hardcoded command strings (not user input),
the command string should be passed directly to bash -c for normal shell
parsing.
Fixes#88
Agent: team-lead
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The sprite/claude.sh script was using 'claude install' which requires
claude to already be on PATH. Changed to use the curl installer which
downloads and installs the binary from scratch.
Fixes#88
Agent: issue-responder
Co-authored-by: B <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Show clear error when --prompt/-p or --prompt-file is used without a
value (previously silently ignored)
- Fix --prompt-file splice index bug when used after --prompt
- Replace echo -e with printf in fly/lib/common.sh for macOS bash 3.x
compatibility
- Fix incorrect env var name in README (DIGITALOCEAN_TOKEN -> DO_API_TOKEN)
- Add missing agent entries (gptme, OpenCode, Plandex) to 11 cloud READMEs
- Add all 13 agents to Civo README (previously only had 3)
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When sprite version output doesn't match the expected format, the message
now omits the version rather than displaying "unknown". Also broadened the
version regex to match versions without 'v' prefix.
Fixes#79
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
The redirect `> /dev/null 2>&1` was being escaped by `run_sprite`'s
`printf %q`, causing the command to be interpreted incorrectly:
/usr/bin/bash: line 1: claude install > /dev/null 2>&1: No such file or directory
Removing the redirect allows users to see installation progress and
simplifies the command. Installation success is already verified by
the subsequent check on line 33.
Fixes#80
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Enhance UX across CLI and cloud providers with actionable error messages:
1. Modal sandbox creation failures now provide:
- Detailed error output from Python SDK
- Common causes (auth expired, quota issues, network)
- Step-by-step troubleshooting (re-auth, check quota, status page)
2. Modal CLI installation failures now explain:
- Missing pip/pip3 (with installation commands)
- Permission issues (suggest --user flag)
- Manual installation steps
3. Sprite connectivity failures now include:
- Commands to check sprite status and logs
- Steps to recreate sprite
- Support contact information
4. Sprite CLI installation now:
- Catches installation failures with helpful error messages
- Verifies installation succeeded before proceeding
- Provides manual installation instructions
5. CLI script download failures improved:
- Distinguish between 404 (doesn't exist) and other errors
- Provide specific next steps for each scenario
- Suggest checking matrix for implementation status
All error messages follow the pattern:
- What went wrong
- Why it might have happened (common causes)
- What to do next (actionable steps)
Agent: ux-engineer
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
- Modified ensure_sprite_installed() to check if sprite is already installed
- When sprite is found, log version and skip installation
- Prevents unnecessary reinstalls when sprite CLI is already present
Fixes#63
Agent: community-coordinator
Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Root causes:
- `clear` command fails with exit 1 when TERM is not set (test env has
no terminal), crashing the script due to set -e. Guard with || true.
- Test patterns for Claude settings/state uploads used old temp file
naming convention (/tmp/claude_settings, /tmp/claude_global) that no
longer matches the paths generated by upload_config_file +
upload_file_sprite (/tmp/*settings.json, /tmp/*.claude.json).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The upstream OpenCode installer pipes `curl -# -L | tar xz` which fails
in container exec environments (Sprite, E2B, Modal, Daytona) where the
binary stream gets corrupted through the exec layer, producing
"gzip: stdin: not in gzip format" errors.
Added opencode_install_cmd() to shared/common.sh that downloads the
binary to a file first, then extracts it. Updated all 17 opencode.sh
scripts to use this robust method instead of the upstream installer.
The previous fix (#44) only addressed Sprite with a hardcoded
linux-x86_64 architecture. This fix detects OS/arch dynamically and
applies to all cloud providers.
Fixes#42
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The upstream install script (curl|bash) fails inside Sprite sandboxes
because the nested curl|tar pipeline receives non-gzip content. Replace
with direct binary download from GitHub releases which is more reliable
in sandboxed/piped execution contexts.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Plandex is an open source AI coding agent for complex tasks (15k+ GitHub
stars, multiple HN frontpage posts). It natively supports OpenRouter via
OPENROUTER_API_KEY environment variable and installs via a single curl
command. Go-based CLI with sandbox and version control for AI changes.
Implemented on all 14 clouds: sprite, hetzner, digitalocean, vultr,
linode, lambda, aws-lightsail, gcp, e2b, modal, fly, civo, scaleway,
daytona.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: extract shared test helpers and utilities
Created centralized test-helpers.ts module to eliminate duplication across test files:
**Extracted Helpers:**
- createMockManifest() - Reusable mock manifest data
- createEmptyManifest() - Empty manifest for edge cases
- createConsoleMocks() - Console spy setup
- createProcessExitMock() - Process exit mock
- restoreMocks() - Mock cleanup utility
- mockSuccessfulFetch() - Simplified successful fetch mock
- mockFailedFetch() - Simplified failed fetch mock
- mockFetchWithStatus() - Fetch mock with custom status
- setupTestEnvironment() - Test directory and env setup
- teardownTestEnvironment() - Cleanup utility
**Deduplication Impact:**
- commands.test.ts: Removed 50+ lines of duplicate mock setup
- manifest.test.ts: Removed 80+ lines of duplicate manifest data and setup code
- integration.test.ts: Removed 40+ lines of duplicate setup/teardown
**Benefits:**
- Single source of truth for test fixtures
- Consistent mock patterns across all tests
- Easier maintenance - changes to test setup in one place
- Improved test readability
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* refactor: Add non-interactive mode for agent execution
Implements --prompt and --prompt-file flags to enable non-interactive
agent execution. This allows users to:
- Execute agents with a prompt and exit automatically
- Use spawn in CI/CD pipelines and automation scripts
- Pass prompts via command line or file
Changes:
- TypeScript CLI: Parse --prompt/-p and --prompt-file flags
- Security: Add validatePrompt() to prevent command injection
- Commands: Pass prompt via SPAWN_PROMPT env var to bash scripts
- Bash scripts: Detect SPAWN_PROMPT and fork interactive/non-interactive
- Help text: Document new flags with examples
Implementation:
- claude.sh: Use 'claude -p' for non-interactive execution
- aider.sh: Use 'aider -m' for non-interactive execution
- shared/common.sh: Add execute_agent_non_interactive() helper
Security:
- Validates prompts for command injection patterns
- Length limit: 10KB max
- Blocks $(), backticks, piping to bash/sh
- Uses printf %q for proper shell escaping
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* docs: Add testing guide for non-interactive mode
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
The refactor in f9dd9a7 hardcoded /root/ as the upload destination for
Claude Code and OpenClaw config files, breaking all non-root providers
(Lambda, AWS Lightsail, GCP, Sprite, E2B, Modal, Fly). Upload to /tmp/
first then mv to ~/ via run_callback so the remote shell expands ~ to
the correct home directory.
Also add OPENROUTER_API_KEY env var check to sprite scripts (claude,
openclaw, nanoclaw) so the OAuth flow is skipped when the key is already
set, and fix echo -e to printf for macOS bash 3.x compat.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
OpenCode is a Go-based AI coding agent with a terminal TUI (Bubble Tea).
It natively supports OpenRouter as a built-in provider via OPENROUTER_API_KEY.
- Add opencode agent to manifest.json with env config
- Implement sprite/opencode.sh for Sprite cloud
- Implement hetzner/opencode.sh for Hetzner Cloud
- Add matrix entries (implemented: sprite, hetzner; missing: rest)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Completed ENV_TEMP pattern extraction across remaining providers:
1. Modal: gptme.sh (1 script) - uses inject_env_vars_local
2. GCP: all 10 agent scripts - uses inject_env_vars_ssh
3. Fly.io: all 11 agent scripts - uses new inject_env_vars_fly
- Added inject_env_vars_fly() to fly/lib/common.sh
- Handles both .bashrc and .zshrc (Fly-specific requirement)
4. Sprite: amazonq, cline, gemini (3 scripts) - uses inject_env_vars_sprite
Total scripts converted in this commit: 25
Total scripts converted in Round 25 Task #1: 78 scripts
Each conversion replaces 11-15 lines of temp file management with a single
function call that handles creation, permissions, content generation, upload,
sourcing, and cleanup.
The only remaining ENV_TEMP patterns are DOTENV_TEMP in nanoclaw scripts,
which are agent-specific .env files and should remain as-is.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* feat: add gptme agent to spawn matrix
Add gptme (https://github.com/gptme/gptme) - a personal AI agent in the
terminal with tools for code editing, terminal commands, web browsing,
and more. Natively supports OpenRouter via OPENROUTER_API_KEY.
- Add gptme agent entry to manifest.json with OpenRouter env vars
- Implement sprite/gptme.sh deployment script
- Implement hetzner/gptme.sh deployment script
- Add "missing" matrix entries for remaining 8 clouds
- Update README.md with usage instructions for Sprite and Hetzner
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Fly.io cloud provider with claude and aider agents
Add Fly.io as a new cloud provider using the Machines REST API for
provisioning and flyctl CLI for SSH access. Docker-based machines
with pay-per-second pricing.
- Create fly/lib/common.sh with Fly.io Machines API integration
- Implement fly/claude.sh for Claude Code deployment
- Implement fly/aider.sh for Aider deployment
- Update README.md with Fly.io usage instructions and env vars
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add gemini, amazonq, cline, gptme to Fly.io
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add openclaw, nanoclaw, goose, codex, interpreter to Fly.io
Implements 5 new agent scripts for the Fly.io cloud provider:
- fly/openclaw.sh: OpenClaw with gateway + TUI, model selection, config
- fly/nanoclaw.sh: NanoClaw WhatsApp agent with .env configuration
- fly/goose.sh: Block's Goose agent with OpenRouter provider
- fly/codex.sh: OpenAI Codex CLI with OpenRouter base URL override
- fly/interpreter.sh: Open Interpreter with OpenRouter base URL override
All scripts follow the Fly.io pattern (flyctl-based, no IP args for
run_server/interactive_session) and use upload_file for env injection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add gptme agent to 8 remaining clouds
Implement gptme agent scripts for digitalocean, vultr, linode, lambda,
aws-lightsail, gcp, e2b, and modal. Each script follows the exact
pattern of that cloud's existing aider.sh, adapted for gptme's install
and launch commands. Updates manifest.json matrix entries from "missing"
to "implemented".
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add guardrails from insights: CLAUDE.md rules, hooks, pre-commit
Based on usage insights analysis:
CLAUDE.md:
- Shell script rules: curl|bash compat, macOS bash 3.x compat
- Autonomous loop rules: test after each iteration, never revert fixes
- Git workflow rules: always use feature branches
.claude/settings.json:
- PostToolUse hook validates .sh files on every Write/Edit:
syntax check, no relative source, no echo -e, no set -u
.githooks/pre-commit:
- Blocks commits with: syntax errors, relative sources, echo -e,
set -euo, references to deleted functions
- Install: git config core.hooksPath .githooks
README.md:
- Added developer setup section with hook installation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Removed manual rm calls for temp files in sprite/lib/common.sh since
traps now handle cleanup automatically. Combined traps for both temp
files in configure_shell_sprite() function.
Impact: Prevents temp file leaks on crashes/interrupts
Risk: Low - only removing redundant cleanup calls
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- 5 nanoclaw scripts only create DOTENV_TEMP but trap referenced both
- Causes trap to fail silently when trying to rm undefined variable
- Fix: Change trap from both temps to just DOTENV_TEMP
- Affected: digitalocean, hetzner, linode, sprite, vultr
Root cause: Automated trap addition in Round 19 incorrectly detected
these files as using both temp variables (DOTENV_TEMP contains substring
ENV_TEMP which caused false positive in grep check)
- Add trap 'rm -f "${ENV_TEMP}"' EXIT after mktemp creation
- Scripts with DOTENV_TEMP get combined trap for both files
- Remove manual rm calls that are now redundant
- Prevents temp file leaks on early script exit (errors, signals)
- Affects 67 agent scripts across all providers
Impact: Prevents /tmp pollution in production deployments
Score: 90 (Impact: 9, Confidence: 10, Risk: 1)
Quote INSTANCE_STATUS_POLL_DELAY, SSH_RETRY_DELAY, and
SPRITE_CONNECTIVITY_POLL_DELAY to prevent potential word splitting
issues with unusual values.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Separated local variable declaration from command substitution assignment
in upload_file_sprite function to avoid masking return values.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Protects against 'unbound variable' errors even if set -u is
re-enabled or inherited. Every [[ -n "$UPPER_VAR" ]] pattern now
uses [[ -n "${UPPER_VAR:-}" ]] to safely default to empty.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The autonomous refactoring added `set -euo pipefail` but the scripts
check optional env vars with `[[ -n "$VAR" ]]` which is a fatal error
under nounset when the var isn't set (e.g. SPRITE_NAME, OPENROUTER_API_KEY).
Fix: downgrade to `set -eo pipefail` across all 42 affected files.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When scripts run via `bash <(curl ...)`, BASH_SOURCE resolves to
/dev/fd/N, making the relative path `../../shared/common.sh` fail.
Fix: add remote fallback — try local file first, fall back to
fetching shared/common.sh from GitHub via eval+curl.
Applied to all 5 refactored lib/common.sh files (sprite, hetzner,
digitalocean, vultr, linode).
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three issues broke the OAuth callback server on macOS:
1. echo -e doesn't work in bash 3.x — \r\n appears as literal text
in the HTTP response, browser gets malformed headers.
Fix: pre-write response with printf to a file before the subshell.
2. local variables inside ( ... ) & subshell — undefined behavior in
bash 3.x since subshells aren't function scope.
Fix: use plain variables in subshells.
3. ((elapsed++)) when elapsed=0 evaluates to falsy — set -e kills
the script on the first iteration of the timeout loop.
Fix: use elapsed=$((elapsed + 1)) instead.
Also simplified nc_listen detection to only check for BusyBox
(the -p flag check could misfire on macOS nc).
Applied to all 10 lib/common.sh files.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
macOS ships bash 3.x which doesn't support nested process substitution.
When scripts are run via `bash <(curl ...)`, the inner `source <(curl ...)`
for loading common.sh fails silently, causing "command not found" errors.
Fix: replace `source <(curl -fsSL URL)` with `eval "$(curl -fsSL URL)"`
across all 100 agent scripts. eval+curl works on bash 3.x and newer.
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Cline is an open-source AI coding agent for the terminal.
Works with OpenRouter via OPENAI_BASE_URL override.
- Implemented on all 7 clouds
- Matrix now 10 agents x 7 clouds = 70/70 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
AWS's AI coding assistant, works with OpenRouter via OPENAI_BASE_URL override.
Installed via official installer script, launched with `q chat`.
- Implemented on all 7 clouds
- Matrix now 9 agents x 7 clouds = 63/63 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Google's open-source coding agent, works with OpenRouter via
OPENAI_BASE_URL override and GEMINI_API_KEY env var.
- Implemented on all 6 clouds: sprite, hetzner, digitalocean, vultr, linode, aws-lightsail
- Matrix now 8 agents x 6 clouds = 48/48 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Open Interpreter provides a natural language interface for computer control.
Works with OpenRouter via OPENAI_BASE_URL=https://openrouter.ai/api/v1.
- Implemented on all 5 clouds: sprite, hetzner, digitalocean, vultr, linode
- Matrix now 7 agents x 5 clouds = 35/35 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Goose is Block's open-source model-agnostic AI coding agent.
Supports OpenRouter via GOOSE_PROVIDER=openrouter env var.
- sprite/goose.sh, hetzner/goose.sh, digitalocean/goose.sh
- Matrix now 5 agents x 3 clouds = 15/15 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Aider is the most popular open-source AI pair programming CLI.
Natively supports OpenRouter via OPENROUTER_API_KEY env var
and --model openrouter/... flag.
- sprite/aider.sh, hetzner/aider.sh, digitalocean/aider.sh
- Matrix now 4 agents x 3 clouds = 12/12 implemented
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add styled success page with CSS-animated checkmark, fade-in messaging,
and auto-close after 3 seconds with fallback text if browser blocks it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add nc_listen helper that detects busybox nc and uses -p flag accordingly
- Add termux-open-url support to open_browser
- Deduplicate inline browser opener in try_oauth_flow to use open_browser
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add NanoClaw spawn script
NanoClaw is a lightweight WhatsApp-based Claude AI assistant that runs
agents in isolated containers. This script sets up a sprite with
nanoclaw pre-configured: clones the repo, installs dependencies,
configures the API key, and launches in dev mode for WhatsApp QR auth.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Fix verify_sprite_connectivity exiting script early after single failed check
Retry connectivity up to 6 attempts (30s) instead of trying once and
silently continuing, which caused the next sprite exec to fail under set -e.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add test harness for spawn scripts
Mocks the sprite CLI and runs each script end-to-end verifying:
- common.sh sources correctly and all functions resolve
- Log functions write to stderr (not stdout)
- Env var flow (SPRITE_NAME, OPENROUTER_API_KEY)
- Sprite commands called in correct order
- Temp files created and cleaned up
- Each script reaches its final interactive launch
Usage: bash test/run.sh
42 tests, all passing.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Retry connectivity up to 6 attempts (30s) instead of trying once and
silently continuing, which caused the next sprite exec to fail under set -e.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
