Sandboxed VM / container#1 of 16 in category
Writer Action Agent
Writer · Launched Sep 2025
Enterprise agent from Writer (content platform). GAIA Level 3 leader at 61% — surpassed Manus mid-2025.
Visit Writer Action Agent →Enterprise contract
1
Benchmarks scored
61.0
Peak score
0
Article mentions
No
Open source
Benchmark performance
GAIA (General AI Assistants)
3-level benchmark for general AI assistants. Level 3 is the hardest. Current SOTA Level 3: Writer Action Agent at 61%.
61.0
★ SOTA
Human: 92%Benchmark docs →
Other sandboxed vm / container agents
The 16 agents in this category, ranked by peak benchmark.
| Agent | Maker | Launch | Peak | Pricing |
|---|---|---|---|---|
| Manus AI | Butterfly Effect | 2025-03 | 57.7 | Subscription (invite-only at launch) |
| OpenHandsOSS | All-Hands AI | 2024-03 | 53.0 | Free (self-hosted) or All-Hands Cloud |
| Replit Agent 4 | Replit | 2026-03 | — | Core $25/mo + credits; Pro $100/mo + credits |
| E2BOSS | E2B | 2023-11 | — | Free tier + usage-based |
| DaytonaOSS | Daytona | 2024-05 | — | Free (OSS) + cloud paid |
| Modal Sandboxes | Modal Labs | 2024-09 | — | $0.00003942/CPU-sec |
| Bedrock AgentCore | Amazon | 2025-10 | — | AWS usage-based |
| Gemini Enterprise (Agentspace) | 2024-12 | — | Enterprise contract | |
| Salesforce Agentforce 360 | Salesforce | 2024-09 | — | Per-conversation |
| IBM watsonx Orchestrate | IBM | 2025-05 | — | Enterprise contract |
Quick facts
- Type
- Sandboxed VM / container
- Maker
- Writer
- Launch
- 2025-09-01
- Open source
- No
- Pricing
- Enterprise contract
- Benchmarks scored
- 1
- Article mentions
- 0
- Rank in category
- #1 of 16