Item detail
github.com

Fullive-AI/Anima

Fullive-AI/Anima is a apache-2.0 open-source agent os in RepoRadar's Fullive-AI/Anima (Apache-2.0, Fullive AI) is the section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 9.1 out of 10.

Score8.0
Popularity1102.0
Risklow
TierGold
Score breakdown
Usefulness8.0
Novelty9.0
Momentum8.0
Maturity8.8
Open-source/build8.4
Evidence8.0
Workflow potential9.1
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for **smart home enthusiasts running Mi Home / MIoT devices who want an AI-driven agent OS** — Anima is the Apache-2.0 open-source Agent OS for hardware intelligence, connects smart home devices to a runnable LLM Brain with long-term Memory, per-device Skills, multi-LLM failover (DeepSeek / Qwen / GLM), FastAPI orchestration + Spring Boot 3.5 gateway with Resilience4j circuit breaker + Lang

Who should use it

**Smart home enthusiasts running Mi Home / MIoT devices who want an AI-driven agent OS** — Anima is the Apache-2.0 open-source Agent OS for hardware intelligence, connects smart home devices to a runnable LLM Brain with long-term Memory, per-device Skills, multi-LLM failover (DeepSeek / Qwen / GLM)**Teams building context-aware home automation** — Per-device Skills encode domain knowledge (e.g. 'when CO2 > 1000ppm and humidity > 70%, run the air purifier on high for 20 minutes, then drop to medium')**Teams that need multi-LLM failover** — Resilience4j circuit breaker aggregates DeepSeek / Qwen / GLM with automatic rotation on provider failure**Teams that need observability** — Langfuse full call-tree visibility across the agent runtime; trace ID propagation across the FastAPI / Spring Boot boundary**Teams that need per-tenant metering** — AOP aspect captures token / cost without code changes, aggregated by tenant**Teams that need a production-grade agent runtime** — SSE progress streaming, single-segment regeneration, rolling log archives, Postgres + Redis + MinIO data tier**Teams that need a dashboard** — React + Vue 3 + Vite + Vue Flow + Pinia + Tailwind dashboard for visualizing device state, agent decisions, and memory**Mi Home / MIoT users** — auto-discovery of devices on the local network, full control of lights / AC / humidifiers / purifiers / speakers**Developers who want to extend Anima** — per-device Skills are pluggable; new device types can be added with a Skill definition and an adapter**Apache-2.0 commercial platforms** — plain Apache-2.0, no per-file carve-outs, no SaaS-embedding caveat, no commercial-use threshold**Multi-language teams** — English + Chinese README and docs (中文 README.zh-CN.md)Evaluation: prerequisites — Python 3.11–3.13, Java 17+, Node.js for the dashboard, Docker for the data tier. (1) Clone — `git clone https://github.com/Fullive-AI/Anima.git && cd Anima`. (2) Bring up the data tier — `docker compose up -d postgres redis minio`. (3) Configure backend env — `cp .env.example .env`, set `DEEPSEEK_API_KEY` / `QWEN_API_KEY` / `GLM_API_KEY` (at least one required for the LLM Brain). (4) Run the FastAPI orchestrator — `uvicorn anima.orchestrator:app --reload`. Listens on http://localhost:8000. (5) Run the Spring Boot gateway — `cd gateway && ./mvnw spring-boot:run` (or `./gradlew bootRun`). Listens on http://localhost:8080. (6) Run the dashboard — `cd dashboard && npm install && npm run dev`. Opens http://localhost:3000. (7) Discover devices — Anima will auto-discover Mi Home / MIoT devices on your local network. (8) Configure Skills — pick a device type, review the per-device Skill, customize the action thresholds (CO2 / humidity / time-of-day). (9) Test the agent — say 'make the bedroom comfortable' — Anima reads the current sensor data, the user memory, and the per-device Skills, and plans an action sequence. For the open-source status: plain Apache-2.0, Fullive AI, no per-file carve-out, no SaaS-embedding caveat, no commercial-use threshold. For the maturity caveat: at 1102 stars and 35 forks, Anima is a relatively new project with Mi Home / MIoT as the only supported protocol — fine for early adoption in the Mi Home ecosystem, monitor releases for stability and new hardware protocol support

Who should skip it

Skip Fullive-AI/Anima unless the captured evidence suggests it solves a problem you are actively working on.

About this signal

Fullive-AI/Anima is tracked by RepoRadar as a apache-2.0 open-source agent os in the Fullive-AI/Anima (Apache-2.0, Fullive AI) is the section. It was first seen on 2026-06-26 and last updated on 2026-06-26. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, Fullive-AI/Anima is strongest on workflow potential (9.1) and novelty (9.0) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Fullive-AI/Anima a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1102.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

maturity caveat — at 1102 stars and 35 forks; Anima is a relatively new project with Mi Home / MIoT as the only supported hardware protocol; fine for early adoption in the Mi Home ecosystem; monitor releases for stability and new hardware protocol support. Setup complexity: requires Python 3.11–3.13.

Evidence links
Closest alternatives / related signals
animafullive-aifulliveagent-oshardware-intelligencesmart-homemi-homemiot