Front 01
Open-Source Engine
$0 · AGPL-3.0
The Castor MCP engine, one command.
$ npx -y mcp-castor install --client all- 3 MCP tools, 5-layer sandbox
- 27-grammar AST syntax gate
- vLLM, llama.cpp, Ollama profiles
Pair Claude Code, Cursor, or Gemini with your own GPU — or run 100% local and air-gapped. Open-source engine, plus turnkey GPU & vLLM setup for teams.
$ npx -y mcp-castor install --client allRunning a team? We set up your GPUs, vLLM, and agent plumbing in 48 hours →
SESSION KV CACHE · 93.8% HIT · RTX 3090 (W4A16)
Effective Prefill
3,247 tok/swarm + coldDecode (n=4 / n=1)
260.0 / 70.4tok/s aggregate / sustainedSession KV Hit
93.8%across 2.77B tokensLocal GPU Cost
$0.0000~$0.001 power / token-loopRTX 3090 (24 GB) · Qwen3.8-27B-W4A16 · vLLM 0.33.0 · 244.6 W · 56 °C
78-Day RTX 3090 Benchmarks →Keep cloud models for high-level planning. Run the heavy tool loop on your own GPUs — or go 100% local.
Same task · three execution modes
Turn 1 (cloud)
~3.2K tokens ≈ $0.01
Turns 2–40 (local)
260 tok/s (n=4) on your GPU
Session KV cache
93.8% hit across the loop
Total cost
~$0.01 · 99.6% under cloud
The frontier model issues one ~3.2K-token planning brief (≈$0.01). The remaining 39 file, AST, and test turns execute on your local GPU at ~$0.0014 electricity each, reusing the session KV cache at a 93.8% hit — power cost, not tokens billed.
01 / Cloud + Local Hybrid
Pair Claude Code, Cursor, or Gemini with local vLLM, llama.cpp, or Ollama in one command.
02 / 100% Local & Air-Gapped
Zero cloud dependencies, compile-time offline binary, and 5-layer OS sandboxing for sensitive repositories.
03 / Turnkey Setup & Plumbing
We size your GPUs for the workload, configure vLLM 0.33.0 continuous batching and prefix caching, and wire your team’s workflow in 48 hours.
effective prefill
n=4 concurrent decode
session KV cache hit
local power cost
vs 6,044.48 cloud API
Estimate your monthly token burn, hybrid savings, and GPU hardware break-even.
Workload
Frontier lead
Annual net savings
$6,481Cloud-Only / Mo
$638Castor Hybrid / Mo
$981× RTX 5090 Workstation (~$4,500)
≈ 8.3 months
Open-source for individual engineers. Fixed-scope GPU setup, vLLM tuning, and custom plumbing for teams.
Agents
Engines
Models
Hardware
Front 01
$0 · AGPL-3.0
The Castor MCP engine, one command.
$ npx -y mcp-castor install --client allFront 02
$1,500 · 48-Hour Sprint
GPU sizing & vLLM setup in 48 hours.
Front 03
Scoped Build / Retainer
Your stack, wired to your agents.
Front 04
Regulated Pilot
Zero-egress, audit-evidenced, on your hardware.
Pick your front, team size, and GPU status — copy the brief or launch a pre-filled email.