https://github.com/Whatsonyourmind/oraclaw
Decision intelligence for AI agents. 19 algorithms, 12 MCP tools, sub-25ms. Zero LLM cost.
https://github.com/Whatsonyourmind/oraclaw
ai-agents algorithms api bandits decision-intelligence fastify machine-learning mcp optimization typescript
Last synced: about 1 month ago
JSON representation
Decision intelligence for AI agents. 19 algorithms, 12 MCP tools, sub-25ms. Zero LLM cost.
- Host: GitHub
- URL: https://github.com/Whatsonyourmind/oraclaw
- Owner: Whatsonyourmind
- License: mit
- Created: 2026-03-25T01:02:22.000Z (2 months ago)
- Default Branch: master
- Last Pushed: 2026-04-19T21:51:06.000Z (about 1 month ago)
- Last Synced: 2026-04-19T23:36:43.776Z (about 1 month ago)
- Topics: ai-agents, algorithms, api, bandits, decision-intelligence, fastify, machine-learning, mcp, optimization, typescript
- Language: TypeScript
- Homepage: https://web-olive-one-89.vercel.app
- Size: 2.73 MB
- Stars: 7
- Watchers: 0
- Forks: 2
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
- awesome-mcp-servers - Oraclaw - Decision intelligence MCP server with 19 algorithms (bandits, Monte Carlo, constraint optimization, forecasting, anomaly detection, risk analysis, graph algorithms), 12 MCP tools. Install via npx. Supports cloud, home, Apple, Windows, and Linux. ([Read more](/details/oraclaw.md)) `Decision Intelligence` `Algorithms` `Multi Platform` (Data Analysis & Exploration Mcp Servers)
- awesome-claude-code-toolkit - OraClaw - armed bandits, constraint solvers, forecasters, risk models, Q-learning, A*, simulated annealing). Sub-25ms responses, deterministic, 945 tests. `npx @oraclaw/mcp-server` | (Plugins / All Plugins)
- awesome-mcp-servers - Whatsonyourmind/oraclaw - 25ms, zero LLM cost. Install: `npx @oraclaw/mcp-server`. (📊 Data Analysis & Business Intelligence)
README
# OraClaw
[](LICENSE)
[](mission-control)
[](https://modelcontextprotocol.io)
[](web/lib/algorithms.ts)
[](mission-control/scripts/benchmark-all.ts)
[](https://www.npmjs.com/org/oraclaw)
[](https://oraclaw-api.onrender.com)
[](CHANGELOG.md)
**MCP Optimization Tools for AI Agents** -- 12 tools, 19 algorithms, sub-25ms. Zero LLM cost.
Your AI agent can't do math. OraClaw gives it deterministic optimization, simulation, forecasting, and risk analysis through the Model Context Protocol. Every tool returns structured JSON, runs in under 25ms, and costs nothing to compute.
---
## Validation
OraClaw's math has been independently implemented in **12 open-source projects** across AI agent orchestration, time-series tracking, vector search, MIP optimization, and production ML systems -- all within the first 8 days after public launch.
**Selected field implementations** (see [`CHANGELOG.md`](CHANGELOG.md) for the full list):
- [`chernistry/bernstein`](https://github.com/chernistry/bernstein) -- 84⭐ agent orchestration framework. LinUCB contextual router with α=0.3, shadow-evaluation path, interpretable decision reasons. Shipped in `codex/issue-367-linucb-router` 1h40m after the spec correction.
- [`stxkxs/nanohype`](https://github.com/nanohype/nanohype) -- contextual bandit routing, pluggable strategy registry (hash / sliding-TTL / semantic), cost anomaly detection, LinUCB on roadmap. *"Your input shaped a lot of what actually shipped."*
- [`rfivesix/hypertrack`](https://github.com/rfivesix/hypertrack) -- Bayesian/Kalman-style adaptive calorie estimator with phase-aware kcal/kg ramp. Shipped in 0.8.0-beta. *"At this point I think the mathematical model is in a very strong place."*
- [`AlanHuang99/pyrollmatch`](https://github.com/AlanHuang99/pyrollmatch) -- entropy balancing (Hainmueller 2012) with moment constraints + `max_weight` cap. Shipped in v0.1.3.
- [`stffns/vstash`](https://github.com/stffns/vstash) -- IDF-sigmoid relevance weighting. Shipped in v0.17.0.
**Marketplace distribution:**
- ✓ [`punkpeye/awesome-mcp-servers`](https://github.com/punkpeye/awesome-mcp-servers) (84K⭐) -- merged
- ✓ [`TensorBlock/awesome-mcp-servers`](https://github.com/TensorBlock/awesome-mcp-servers) -- merged
- ✓ MCP Registry, Glama (AAA rating), PulseMCP, Smithery, toolsdk-ai -- listed
**Maintainer relationships** (warm technical correspondence): Qdrant, Milvus, NetworkX, Apache DataFusion, DuckDB, pymc-labs.
---
## Quick Start
### 1. MCP Server (recommended for AI agents)
Add to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"oraclaw": {
"command": "npx",
"args": ["-y", "@oraclaw/mcp-server"]
}
}
}
```
Then ask your agent:
> "I have 3 email subject line variants. Which should I send next?"
The agent calls `optimize_bandit` and gets a statistically optimal selection in 0.01ms.
### 2. REST API (no install)
```bash
curl -X POST https://oraclaw-api.onrender.com/api/v1/optimize/bandit \
-H 'Content-Type: application/json' \
-d '{
"arms": [
{"id": "A", "name": "Option A", "pulls": 10, "totalReward": 7},
{"id": "B", "name": "Option B", "pulls": 10, "totalReward": 5},
{"id": "C", "name": "Option C", "pulls": 2, "totalReward": 1.8}
],
"algorithm": "ucb1"
}'
```
Response (<1ms):
```json
{
"selected": { "id": "C", "name": "Option C" },
"score": 1.876,
"algorithm": "ucb1",
"exploitation": 0.9,
"exploration": 0.976,
"regret": 0.1
}
```
Free tier: 25 calls/day, no API key needed.
### 3. npm SDK
```bash
npm install @oraclaw/bandit
```
```typescript
import { OraBandit } from '@oraclaw/bandit';
const client = new OraBandit({ baseUrl: 'https://oraclaw-api.onrender.com' });
const result = await client.optimize({
arms: [
{ id: 'A', name: 'Short Subject', pulls: 500, totalReward: 175 },
{ id: 'B', name: 'Long Subject', pulls: 300, totalReward: 126 },
],
algorithm: 'ucb1',
});
```
14 SDK packages: `@oraclaw/bandit`, `@oraclaw/solver`, `@oraclaw/simulate`, `@oraclaw/risk`, `@oraclaw/forecast`, `@oraclaw/anomaly`, `@oraclaw/graph`, `@oraclaw/bayesian`, `@oraclaw/ensemble`, `@oraclaw/calibrate`, `@oraclaw/evolve`, `@oraclaw/pathfind`, `@oraclaw/cmaes`, `@oraclaw/decide`
---
## Why?
LLMs generate plausible text, not optimal solutions. Ask GPT to pick the best A/B test variant and it applies a heuristic that ignores the exploration-exploitation tradeoff. Ask it to solve a linear program and it hallucinates constraints. OraClaw gives your agent access to real algorithms -- bandits, solvers, forecasters, risk models -- that return mathematically correct answers in sub-millisecond time, without burning tokens on reasoning.
---
## MCP Tool Catalog (12 tools)
| Tool | What It Does | Latency |
|------|-------------|---------|
| `optimize_bandit` | A/B test selection via UCB1, Thompson Sampling, Epsilon-Greedy | 0.01ms |
| `optimize_contextual` | Context-aware personalized selection via LinUCB | 0.05ms |
| `optimize_cmaes` | Black-box continuous optimization (CMA-ES) | 12ms |
| `solve_constraints` | LP/MIP/QP optimization via HiGHS solver | 2ms |
| `solve_schedule` | Energy-matched task scheduling | 3ms |
| `analyze_decision_graph` | PageRank, Louvain communities, bottleneck detection | 0.5ms |
| `analyze_portfolio_risk` | VaR and CVaR (Expected Shortfall) | <2ms |
| `score_convergence` | Multi-source agreement scoring | 0.04ms |
| `score_calibration` | Brier score and log score for prediction quality | 0.02ms |
| `predict_forecast` | ARIMA and Holt-Winters time series forecasting | 0.08ms |
| `detect_anomaly` | Z-Score and IQR anomaly detection | 0.01ms |
| `plan_pathfind` | A* pathfinding with k-shortest paths | 0.1ms |
14 of 17 REST endpoints respond in under 1ms. All under 25ms.
---
## Try It Now
The API is live. No signup required.
```bash
# Bayesian inference
curl -X POST https://oraclaw-api.onrender.com/api/v1/predict/bayesian \
-H 'Content-Type: application/json' \
-d '{"prior": 0.3, "evidence": [{"factor": "positive_test", "weight": 0.9, "value": 0.05}]}'
# Monte Carlo simulation
curl -X POST https://oraclaw-api.onrender.com/api/v1/simulate/montecarlo \
-H 'Content-Type: application/json' \
-d '{"simulations": 1000, "distribution": "normal", "params": {"mean": 100, "stddev": 15}}'
# Anomaly detection
curl -X POST https://oraclaw-api.onrender.com/api/v1/detect/anomaly \
-H 'Content-Type: application/json' \
-d '{"data": [10, 12, 11, 13, 50, 12, 11, 10], "method": "zscore", "threshold": 2.0}'
```
---
## Pricing
| Tier | Calls | Price | Auth |
|------|-------|-------|------|
| **Free** | 25/day | $0 | None |
| **Pay-per-call** | 1K/day | $0.005/call | API key |
| **Starter** | 10K/mo | $9/mo | API key |
| **Growth** | 100K/mo | $49/mo | API key |
| **Scale** | 1M/mo | $199/mo | API key |
**x402 USDC:** AI agents pay $0.01-$0.15 per call with USDC on Base. No subscription, no API key.
---
## Source Code
| Component | Path |
|-----------|------|
| **MCP Server** | [`mission-control/packages/mcp-server/`](mission-control/packages/mcp-server/) |
| **REST API** | [`mission-control/apps/api/`](mission-control/apps/api/) |
| **Algorithms** | [`mission-control/apps/api/src/services/oracle/algorithms/`](mission-control/apps/api/src/services/oracle/algorithms/) |
| **SDK Packages** | [`mission-control/packages/sdk/`](mission-control/packages/sdk/) |
| **LangChain Tools** | [`mission-control/integrations/langchain/oraclaw_tools.py`](mission-control/integrations/langchain/oraclaw_tools.py) |
| **Mobile App** | [`mission-control/apps/mobile/`](mission-control/apps/mobile/) |
| **Dashboard (Next.js)** | [`web/`](web/) |
---
## Building with OraClaw?
We'd love to hear what you're working on. Share your use case, ask questions, or request features:
- [Tell us what you're building](https://github.com/Whatsonyourmind/oraclaw/discussions/1)
- [Report an issue](https://github.com/Whatsonyourmind/oraclaw/issues)
- [Join the conversation on Moltbook](https://www.moltbook.com/u/oraclaw)
---
## Links
- **Live API:** https://oraclaw-api.onrender.com
- **Dashboard:** https://web-olive-one-89.vercel.app
- **npm:** https://www.npmjs.com/org/oraclaw
- **Demo:** https://web-olive-one-89.vercel.app/demo
- **GitHub:** https://github.com/Whatsonyourmind/oracle
---
If this saved your agent from hallucinating math, star us :star:
## License
[MIT](LICENSE)