{"id":51594381,"url":"https://github.com/deepleaper/leaper-agent","last_synced_at":"2026-07-11T17:02:18.418Z","repository":{"id":353916035,"uuid":"1221360810","full_name":"Deepleaper/leaper-agent","owner":"Deepleaper","description":"Self-learning AI agent framework with 6-layer memory evolution engine. Build intelligent agents for any business scenario.","archived":false,"fork":false,"pushed_at":"2026-05-13T10:39:24.000Z","size":14104,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-13T12:35:11.038Z","etag":null,"topics":["ai-agent","ai-employee","cxo","memory","python","self-evolving","telegram"],"latest_commit_sha":null,"homepage":"https://github.com/Deepleaper","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Deepleaper.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-26T05:08:11.000Z","updated_at":"2026-05-13T10:39:28.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Deepleaper/leaper-agent","commit_stats":null,"previous_names":["deepleaper/leaper-agent"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/Deepleaper/leaper-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepleaper%2Fleaper-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepleaper%2Fleaper-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepleaper%2Fleaper-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepleaper%2Fleaper-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Deepleaper","download_url":"https://codeload.github.com/Deepleaper/leaper-agent/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deepleaper%2Fleaper-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35368768,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-11T02:00:05.354Z","response_time":104,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","ai-employee","cxo","memory","python","self-evolving","telegram"],"created_at":"2026-07-11T17:02:16.403Z","updated_at":"2026-07-11T17:02:18.407Z","avatar_url":"https://github.com/Deepleaper.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# 🚀 Leaper Agent\n\n### The Agent Framework That Actually Remembers\n\n### Hermes-Compatible Agent Orchestration + DeepBrain 6-Layer Evolving Memory\n\n[![PyPI version](https://img.shields.io/pypi/v/leaper-agent.svg)](https://pypi.org/project/leaper-agent/)\n[![Downloads](https://img.shields.io/pypi/dm/leaper-agent.svg)](https://pypi.org/project/leaper-agent/)\n[![GitHub stars](https://img.shields.io/github/stars/deepleaper/leaper-agent.svg)](https://github.com/deepleaper/leaper-agent/stargazers)\n[![License](https://img.shields.io/badge/License-BSL--1.1-blue.svg)](LICENSE)\n[![Python](https://img.shields.io/badge/Python-3.10+-blue.svg)](https://python.org)\n\n[Website](https://www.deepleaper.com) · [Quick Start](#-quick-start) · [Why Memory Matters](#-why-memory-matters) · [中国版](https://github.com/deepleaper/leaper-agent-cn)\n\n\u003c/div\u003e\n\n---\n\n## 🤔 The Problem\n\nEvery agent framework gives you tool-calling and multi-model support. **None of them give you real memory.**\n\n- CrewAI? Flat key-value store, resets between runs.\n- AutoGen? Conversation history only, no knowledge evolution.\n- LangGraph? Checkpoints, not understanding.\n- Hermes Agent? Skill files on disk — smart, but static.\n\n**Your agent forgets everything the moment the session ends.**\n\n## 💡 The Solution\n\n**Leaper Agent = [Hermes Agent](https://github.com/hermes-agent) base + [DeepBrain](https://github.com/deepleaper/opc-deepbrain) memory engine.**\n\nWe took the proven Hermes Agent architecture — its agent loop, tool runtime, and multi-provider support — and integrated DeepBrain's 6-layer self-evolving memory engine. The result: **an agent that gets smarter every time you talk to it.**\n\n```\nSession 1: \"I'm building a SaaS product with FastAPI and React.\"\nSession 2: \"What stack should I use for the admin panel?\"\n→ Agent recalls your tech choices, suggests FastAPI Admin + React\n→ No manual context injection. It just knows.\n```\n\n## 🧠 Why Memory Matters\n\n| What happens | Without memory | With DeepBrain |\n|-------------|---------------|----------------|\n| You mention your tech stack | Forgotten next session | Remembered forever, evolves over time |\n| You correct the agent | Same mistake tomorrow | Learns the correction, never repeats |\n| You have 50 conversations | Each starts from zero | Agent builds a knowledge graph of YOU |\n| Knowledge conflicts | Silently contradicts itself | 4-Gate system detects \u0026 resolves conflicts |\n\n### 6-Layer Memory Architecture\n\n```\n┌─────────────────────────────────────────┐\n│  Layer 5: Meta-Knowledge               │\n│  \"I know your tech preferences well,   │\n│   but I'm uncertain about your budget\"  │\n├─────────────────────────────────────────┤\n│  Layer 4: Archived — Historical ref     │\n├─────────────────────────────────────────┤\n│  Layer 3: Consolidated — Cross-session  │\n├─────────────────────────────────────────┤\n│  Layer 2: Long-Term — Validated facts   │\n├─────────────────────────────────────────┤\n│  Layer 1: Short-Term — Recent context   │\n├─────────────────────────────────────────┤\n│  Layer 0: Flash — Current session       │\n└─────────────────────────────────────────┘\n    ↑ Auto-promotion via 4-Gate QC ↑\n    (Relevance · Novelty · Consistency · Utility)\n```\n\nThis isn't RAG. This isn't vector search. This is **knowledge that evolves** — facts get validated, promoted, consolidated, and the agent develops meta-awareness of what it knows well and what it doesn't.\n\n## 🚀 Quick Start\n\n```bash\n# Install\npip install leaper-agent\n\n# Set your API key\nexport OPENAI_API_KEY=sk-xxx\n# or: export ANTHROPIC_API_KEY=sk-ant-xxx\n# or: export GEMINI_API_KEY=xxx\n\n# Create an agent with the CEO Coach template\nleaper create my-agent --template ceo-coach\n\n# Start\nleaper start my-agent\n```\n\n### Deploy as Telegram Bot\n\n```bash\nleaper create my-bot --template ceo-coach --bot-token YOUR_TELEGRAM_TOKEN\nleaper start my-bot\n```\n\n## 🏗️ Architecture\n\n```\n┌─────────────────────────────────────────┐\n│         Leaper Agent Runtime            │\n│    (Hermes-compatible agent loop)       │\n├─────────┬──────────┬──────────┬────────┤\n│ OpenAI  │ Claude   │ Gemini   │ Ollama │\n├─────────┴──────────┴──────────┴────────┤\n│         Agent Orchestration             │\n│    Role templates · Tool calling        │\n├─────────────────────────────────────────┤\n│      🧠 DeepBrain Memory Engine         │\n│   6-Layer · 4-Gate · Zero Dependencies  │\n│   SQLite-only · 100% Local · Evolving   │\n└─────────────────────────────────────────┘\n```\n\n**Key difference from Hermes:** Hermes stores skills as static Markdown files. Leaper Agent's DeepBrain **automatically extracts, validates, and evolves knowledge** from every conversation — no manual curation needed.\n\n## ⚡ Hermes Compatibility\n\nLeaper Agent is built on the Hermes Agent foundation. If you're familiar with Hermes, you'll feel at home:\n\n- Same agent loop architecture\n- Same multi-provider model support\n- Same tool runtime\n- **Plus:** 6-layer evolving memory that Hermes doesn't have\n\n## 🔌 Supported Providers\n\n| Provider | Models | Status |\n|----------|--------|--------|\n| OpenAI | GPT-4o, GPT-4o-mini, o1/o3 | ✅ |\n| Anthropic | Claude Sonnet, Opus, Haiku | ✅ |\n| Google | Gemini 2.0, 2.5 | ✅ |\n| Ollama | Any local model | ✅ |\n\n## 📊 vs Other Frameworks\n\n| | Leaper Agent | Hermes | CrewAI | AutoGen | LangGraph |\n|---|:---:|:---:|:---:|:---:|:---:|\n| Memory that evolves | ✅ 6-layer | ❌ Static files | ❌ Flat KV | ❌ Chat history | ❌ Checkpoints |\n| Knowledge quality control | ✅ 4-Gate | ❌ | ❌ | ❌ | ❌ |\n| Meta-knowledge | ✅ | ❌ | ❌ | ❌ | ❌ |\n| Multi-provider | ✅ | ✅ | ✅ | ✅ | ✅ |\n| Zero memory dependencies | ✅ SQLite only | N/A | ❌ Redis/Qdrant | ❌ | ❌ Vector DB |\n| Hermes compatible | ✅ | ✅ | ❌ | ❌ | ❌ |\n\n## 🇨🇳 China Version / 中国版\n\nFor Chinese LLM providers (DeepSeek, 通义千问, 智谱, Moonshot) + 150 role templates:\n\n```bash\npip install leaper-agent-cn\n```\n\n→ [Leaper Agent CN](https://github.com/deepleaper/leaper-agent-cn)\n\n## 🔗 Ecosystem\n\n| Project | Description |\n|---------|-------------|\n| [OPC DeepBrain](https://github.com/deepleaper/opc-deepbrain) | Standalone memory engine (use in any framework) |\n| [OPC Agent](https://github.com/deepleaper/opc-agent) | Local-first agent with Ollama |\n| [Leaper Agent CN](https://github.com/deepleaper/leaper-agent-cn) | China-optimized with 150 templates |\n\n## 📄 License\n\n[BSL-1.1](LICENSE) — Free for non-competitive use. Converts to Apache-2.0 after 4 years.\n\n## 🤝 Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md).\n\n📧 Contact: [tech@deepleaper.com](mailto:tech@deepleaper.com)\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**Built with ❤️ by [Deepleaper Technology / 跃盟科技](https://www.deepleaper.com)**\n\n*Other agents forget. Leaper Agent evolves.*\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepleaper%2Fleaper-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeepleaper%2Fleaper-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeepleaper%2Fleaper-agent/lists"}