open-multi-agent/open-multi-agent
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
Repository profile
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Tracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-06-10 10:50
1 capture since 2026-06-10
Stars from baseline 0
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-06-10 10:50
package.json
javascript ecosystem,
2 dependencies
pyproject.toml
python ecosystem,
32 dependencies
requirements-dev.txt
python ecosystem,
28 dependencies
requirements.txt
python ecosystem,
3 dependencies
pnpm-lock.yaml
javascript ecosystem,
658 dependencies
examples/vercel-ai-nextjs/package.json
javascript ecosystem,
9 dependencies
packages/core/package.json
javascript ecosystem,
18 dependencies
packages/langchain-cascadeflow/package.json
javascript ecosystem,
16 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
AI agent config detected
Key config paths
Nearest indexed repositories by embedding similarity.
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration
The agent that grows with you
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.