# kvcache-ai/AgentENV > Distributed platform for running isolated agent environments on Firecracker microVMs with snapshot, fork, and OCI image support. Used for large-scale agentic RL training (Kimi K3) and parallel agent workflows. - Magnitude: 2.0 out of 10 — Steady - Stars: 3,530 total · +6 stars today, ≈ 12 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Rust · License: MIT · Created: 2026-07-23 · Last push: 2026-09-24 - GitHub: https://github.com/kvcache-ai/AgentENV · Page: https://gitnova.dev/en/r/kvcache-ai/AgentENV ## Useful for - Run thousands of isolated sandboxes for parallel agentic RL training - Snapshot a running environment and fork it into multiple independent sandboxes - Expose an E2B-compatible API and launch sandboxes via the standard E2B SDK without code changes ## Why it’s here - 6 stars so far today, about 11 expected by the end of the day. - Over the last two days the pace is 2.3× that of the previous week and a half. - GitHub Trending Rust today: #16, +14 stars. - Recent forks include notable developers: @StarpTech (429 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 318 - Issues and pull requests: 314 - Watchers: 12 - Average over the last week: 7 per day - Usual pace: 9 per day - Stars in the last hour (measured): 3 - Latest release: v0.2.2 (2026-09-18) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-08-26 … 2026-09-24: 13, 12, 3, 3, 15, 13, 16, 11, 11, 4, 3, 3, 6, 7, 7, 2, 3, 6, 7, 6, 9, 4, 11, 7, 4, 3, 2, 9, 14, 6 ## Spotted in now - GitHub Trending Rust today: #16, +14 stars ## More in this category 1. **NandhaKishorM/laya** — 8.1 · Peaking · AI agents · Python · +787 stars today, ≈ 1,836 by evening Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities. Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md 2. **google/ax** — 8.1 · Breakout · AI agents · Go · +344 stars today, ≈ 782 by evening A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network… Full card: https://gitnova.dev/en/r/google/ax.md 3. **unreallabsai/unreal-agent** — 7.7 · Breakout · AI agents · Go · +52 stars today, ≈ 182 by evening Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components. Full card: https://gitnova.dev/en/r/unreallabsai/unreal-agent.md 4. **strands-agents/harness-sdk** — 7.4 · Breakout · AI agents · Python · +119 stars today, ≈ 251 by evening Open-source Python and TypeScript SDK for building and running AI agents: agent loop, tools, MCP, memory, multi-agent patterns and tracing in one package. Runs in your process with no hosted control plane and supports multiple model… Full card: https://gitnova.dev/en/r/strands-agents/harness-sdk.md 5. **mikehasa/golive-skill** — 7.3 · Early signal · AI agents · TypeScript · +556 stars today, ≈ 805 by evening Agent Skill and Node CLI that takes an agent-built app live: hosting, database, domain, email and payments on your own accounts. Runs a detect → plan → approve → apply → verify cycle with no hosted backend or telemetry. Full card: https://gitnova.dev/en/r/mikehasa/golive-skill.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-24 13:15 UTC, updated every 30 minutes.