mirage vs nanoclaw
nanoclaw is much bigger: 30.7k stars against 3.6k. Over the days we have tracked them mirage moved +16.6% and nanoclaw +3.6%, so mirage is growing faster right now.
They split the axes: mirage leads on context depth and customization, nanoclaw on model freedom.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Mounts dozens of services (S3, Slack, Gmail, databases, etc.) side-by-side as a single POSIX-like virtual filesystem so agents can use bash-native pipelines across backends.
- Stars
- 3.6k
- Tracked growth
- +16.6%
- Maturity
- ●●●●●
- Last commit
- 24m ago
- Language
- TypeScript
- License
- Apache-2.0
- Cost to run
- Free, self-hosted; external API costs apply
Provides compact, auditable agent runtime with true OS-level container isolation so agents run in separate containers with explicit mounts instead of one large shared process.
- Stars
- 30.7k
- Tracked growth
- +3.6%
- Maturity
- ●●●●●
- Last commit
- 11h ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Your API key (Anthropic/OpenAI) or local models
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | mirage | nanoclaw |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Whole workspace | ●●●●● Related files access |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters/config | ●●●●● Basic gating |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Extensible commands | ●●●●● Code-based customization |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Multiple adapters | ●●●●● Bring-your-own key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● CLI / SDK quickstart | ●●●●● One-script install |
Which one to pick
Pick mirage if…
Unified VFS — pick Mirage when you want agents to access remote services and local files through one POSIX-style filesystem, enabling cross-backend commands, portable workspaces, and embeddable runtimes.
- Context depth: Whole workspace (5/5 against 3/5)
- Customization: Extensible commands (5/5 against 3/5)
Pick nanoclaw if…
Privacy-first — run agents in isolated Docker containers on your own machine with per-agent mounts and the option to use local or BYO models.
- Model freedom: Bring-your-own key (5/5 against 3/5)
What people want from each one
strukto-ai/mirage
Hacker News: Mirage – A programming framework for building type-safe, modular systems drew 317 points and 88 comments.
nanocoai/nanoclaw
Hacker News: Show HN: NanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolation drew 533 points and 224 comments.
Questions people ask
Is mirage better than nanoclaw?
They split the axes: mirage leads on context depth and customization, nanoclaw on model freedom. mirage is worth picking when unified VFS — pick Mirage when you want agents to access remote services and local files through one POSIX-style filesystem, enabling cross-backend commands, portable workspaces, and embeddable runtimes.
Which of mirage and nanoclaw keeps my code private?
mirage: Self-hostable (4/5). nanoclaw: Self-hostable (4/5).
What does each one cost to run?
mirage: Free, self-hosted; external API costs apply. nanoclaw: Your API key (Anthropic/OpenAI) or local models.
Full profiles: strukto-ai/mirage and nanocoai/nanoclaw. Everything else in Runtimes & sandboxes.