{"id":50801671,"url":"https://github.com/ukkit/chat-o-llama","last_synced_at":"2026-06-12T20:34:16.698Z","repository":{"id":296235357,"uuid":"992682537","full_name":"ukkit/chat-o-llama","owner":"ukkit","description":"🦙 chat-o-llama: A lightweight, modern web interface for AI conversations with support for both Ollama and llama.cpp   backends. Features persistent conversation management, real-time backend switching, intelligent context   compression, and a clean responsive UI.","archived":false,"fork":false,"pushed_at":"2026-06-09T06:38:52.000Z","size":1397,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-06-09T08:26:28.804Z","etag":null,"topics":["ai-chat","chat","chat-interface","chat-o-llama","chatbot","conversation-history","cpu-only","developer-tools","flask","lightweight","llama-cpp","llamacpp","local-ai","offline-ai","ollama","privacy-focused","python","self-hosted","sqlite"],"latest_commit_sha":null,"homepage":"https://coff.ee/ukkit","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ukkit.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-05-29T14:46:56.000Z","updated_at":"2026-06-09T06:38:56.000Z","dependencies_parsed_at":"2025-07-17T18:06:31.068Z","dependency_job_id":"0366ec74-6fe0-4436-ad73-b14b4e2ad501","html_url":"https://github.com/ukkit/chat-o-llama","commit_stats":null,"previous_names":["ukkit/chat-o-llama"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ukkit/chat-o-llama","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fchat-o-llama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fchat-o-llama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fchat-o-llama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fchat-o-llama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ukkit","download_url":"https://codeload.github.com/ukkit/chat-o-llama/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fchat-o-llama/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34262155,"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":"2026-06-12T02:00:06.859Z","response_time":109,"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-chat","chat","chat-interface","chat-o-llama","chatbot","conversation-history","cpu-only","developer-tools","flask","lightweight","llama-cpp","llamacpp","local-ai","offline-ai","ollama","privacy-focused","python","self-hosted","sqlite"],"created_at":"2026-06-12T20:34:15.811Z","updated_at":"2026-06-12T20:34:16.689Z","avatar_url":"https://github.com/ukkit.png","language":"Python","funding_links":["https://buymeacoffee.com/ukkit"],"categories":[],"sub_categories":[],"readme":"# Chat-O-Llama 🦙\n\n### ⚡ Best of Both Worlds: Ollama AND Llama.cpp — switch backends on the fly!\n\n---\n\nA lightweight web interface for Ollama and llama.cpp with markdown rendering, syntax highlighting, intelligent context compression, and persistent conversation management. Designed to run on low-powered hardware.\n\n![Ollama Chat Interface](https://img.shields.io/badge/Interface-Web%20Based-blue)\n![Python](https://img.shields.io/badge/Python-3.10%2B-green)\n![Ollama](https://img.shields.io/badge/connect-OLLAMA-blue)\n![Llama.cpp](https://img.shields.io/badge/connect-LLAMA.CPP-blue)\n![License](https://img.shields.io/badge/License-MIT-yellow)\n[![Buy Me a Coffee](https://img.shields.io/badge/Buy%20Me%20A%20Coffee-%E2%98%95-yellow)](https://buymeacoffee.com/ukkit)\n\n## ⁉️ Why Another App?\n\nBecause **_why not_**? Having choices puts you in control.\n\n## ✨ Features\n\n- **Ollama + llama.cpp** — Switch backends on the fly; automatic fallback\n- **Context Compression** — Compresses long conversations to fit model context windows (rolling window, intelligent summary)\n- **Conversations** — Create, rename, search, and persist chat sessions in SQLite\n- **Markdown + Metrics** — Rendered responses with token count, speed, and timing\n- **Lightweight** — Runs on Raspberry Pi 4 with 8 GB RAM\n\n## 🚀 Quick Start\n\n**Automatic installation (recommended):**\n\n```bash\ncurl -fsSL https://github.com/ukkit/chat-o-llama/raw/main/install.sh | bash\n```\n\nThis will:\n- Install Python and uv if missing\n- Install Ollama if not present\n- Download and set up Chat-O-Llama\n- Start the service at http://localhost:3113\n\n**Manual installation:**\n\n```bash\ngit clone https://github.com/ukkit/chat-o-llama.git\ncd chat-o-llama\n\n# Activate the git hook for automatic versioning\ngit config core.hooksPath .githooks\n\n# Using uv (recommended)\nuv venv venv\nsource venv/bin/activate\nuv sync\n\n./chat-manager.sh start\n```\n\n*Installing llama.cpp:*\n\n```bash\ncurl -fsSL https://github.com/ukkit/chat-o-llama/raw/main/install-llamacpp.sh | bash\n```\n\nFor detailed steps, see [install.md](./docs/install.md).\n\n## 📸 Screenshots\n\n\u003cdetails\u003e\u003csummary\u003e\u003cb\u003eApp Screenshots\u003c/b\u003e\u003c/summary\u003e\n\n![chat-o-llama - First Screen](./docs/assets/screenshot1.png)\nFirst screen after installation\n\n![chat-o-llama - Switch between ollama and llama.cpp](./docs/assets/screenshot2.png)\nAvailable backends — Ollama and Llama.cpp\n\n![chat-o-llama - Quick switch](./docs/assets/screenshot3.png)\nQuick switch between Ollama and Llama.cpp\n\n![chat-o-llama - Chat in llama.cpp](./docs/assets/screenshot4.png)\nChat in llama.cpp with visible L indicator\n\n![chat-o-llama - Chat in Ollama](./docs/assets/screenshot5.png)\nChat in Ollama with visible O indicator\n\n![chat-o-llama - Quick Switch back](./docs/assets/screenshot6.png)\nThinking styling\n\n\u003c/details\u003e\n\n## 🆕 What's new\n\n**2026.0609.1208**\n- Startup time reduced from 10–40s to ~500ms — backend health checks deferred to first request\n- Compression subsystem and DB tables only initialised when `compression.enabled = true`\n- `MCPManager` reduced to one shared lazy instance; no longer created at import time\n- highlight.js, marked.js, and github-dark CSS bundled locally — UI works fully offline\n- Removed `psutil` (unused dependency)\n- Context compression decoupled from message storage — `ConversationManager` returns raw messages only; compression is an explicit step via `build_chat_context()`\n- `ContextCompressor` is now the single entry point for all compression operations\n- Removed `mcp` from required dependencies (install separately if needed)\n- Updated Flask, requests, and llama-cpp-python to current versions\n- Domain glossary added (`CONTEXT.md`)\n\n**2025.0718.0000** _(last semantic release: v2.1.0)_\n- Collapsible sidebar with Llama icon\n- Enhanced chat selection identification\n- Disable chatbox for unavailable models\n- Model dropdown validation bug fix\n\n## 🔧 Troubleshooting\n\n**Common issues:**\n\n- Port in use? Run: `./chat-manager.sh start 3030`\n- No models? Install one: `ollama pull tinyllama`\n- Backend issues? Check status: `./chat-manager.sh backend status`\n\n## 📚 Documentation\n\n\u003cdetails\u003e\u003csummary\u003eDocumentation\u003c/summary\u003e\n\n| Document | Description |\n|---------|-------------|\n| [Installation Guide](./docs/install.md) | Detailed installation instructions |\n| [Features](./docs/features.md) | Complete features overview |\n| [Process Management](./docs/chat_manager_docs.md) | Using chat-manager.sh for service control |\n| [Configuration](./docs/config.md) | Configuration options and settings |\n| [API Reference](./docs/api.md) | REST API documentation |\n| [Troubleshooting](./docs/troubleshooting.md) | Common issues and solutions |\n\n\u003c/details\u003e\n\n## 🖥 Tested Hardware\n\n| Device | CPU | RAM | OS |\n|---------|-------------|---------|-------------|\n| Raspberry Pi 4 Model B Rev 1.4 | ARM Cortex-A72 | 8GB | Raspberry Pi OS |\n| Dell Optiplex 3070 | i3-9100T | 8GB | Debian 12 |\n| Nokia Purebook X14 | i5-10210U | 16GB | Windows 11 Home |\n\n## 🐛 Known Issues\n\n_Quite a few known issues we are working on._\n\n---\n\nIf you find this project helpful, consider:\n\n- 🌟 Starring the repository on GitHub\n- 🤝 [Supporting development](https://buymeacoffee.com/ukkit)\n- 🐛 Reporting bugs and suggesting features\n\n## License\n\nMIT License — see [LICENSE](LICENSE) for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukkit%2Fchat-o-llama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fukkit%2Fchat-o-llama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukkit%2Fchat-o-llama/lists"}