🗂️mirage
strukto-ai/mirage · homepage ↗
The World's First Unified Virtual Filesystem For AI Agents
⭐ Popular: 3k stars, gaining about 64 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Lets LLM agents reach S3, Google Drive, Slack, Gmail, GitHub, Notion, Postgres and around 50 other backends through ordinary bash commands, so agents avoid learning a separate API or SDK per service.
- Targets developers building agents on frameworks like OpenAI Agents SDK, Vercel AI SDK, LangChain, Pydantic AI and OpenHands, giving them one filesystem interface instead of many integrations.
- Supports cloning, snapshotting and versioning workspaces, which helps teams reproduce agent runs across environments.
under the hood
- Mounts each service as part of a single virtual filesystem using FUSE-based mounts, so it runs only on macOS or Linux and needs Python 3.11 or newer and Node.js 20 or newer.
- Requests pass from the agent through Mirage's bash and VFS layer to a dispatcher and cache, backed by a metadata index cache with a 10-minute default TTL and a 512 MB file cache, with optional Redis for distributed caching across workers.
- Written in TypeScript and Python with embeddable in-process SDKs, distributed via pip as mirage-ai and npm as @struktoai/mirage-node under Apache 2.0.
Radar summary, generated from the project's public sources
star history
- PR#34 2k 2026-05-20
- now 3k + 2k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Deep in the understory, shipping hard, still flying under the radar.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Unified virtual filesystem for AI agents
similar projects
compare these →- 🌊 Ruflo
20× the stars
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
68k ACTIVE - 🔗 Composio
8.6× the stars
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
30k ACTIVE - 🦌 DeerFlow
Python · 23× the stars
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
80k ACTIVE
comments
Sign in with GitHub to add your blip on mirage.