{"id":15165818,"url":"https://github.com/rb81/convollama","last_synced_at":"2026-01-21T21:35:11.861Z","repository":{"id":250020578,"uuid":"833143085","full_name":"rb81/convollama","owner":"rb81","description":"A simple Python application that facilitates AI-driven conversations using Ollama.","archived":false,"fork":false,"pushed_at":"2025-08-08T07:17:59.000Z","size":4288,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-13T12:42:19.397Z","etag":null,"topics":["ai-conversations","large-language-models","llama3","ollama","small-language-models","wizardlm2"],"latest_commit_sha":null,"homepage":"","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/rb81.png","metadata":{"files":{"readme":"README.md","changelog":null,"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}},"created_at":"2024-07-24T12:44:21.000Z","updated_at":"2025-08-08T07:18:03.000Z","dependencies_parsed_at":"2025-08-24T13:26:50.283Z","dependency_job_id":"6766d665-453d-4a76-bd37-3e3a85f79933","html_url":"https://github.com/rb81/convollama","commit_stats":{"total_commits":12,"total_committers":1,"mean_commits":12.0,"dds":0.0,"last_synced_commit":"e0f0d75255d6ea00b92b762ac5848c295d42d8d7"},"previous_names":["rb81/convollama"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rb81/convollama","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rb81%2Fconvollama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rb81%2Fconvollama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rb81%2Fconvollama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rb81%2Fconvollama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rb81","download_url":"https://codeload.github.com/rb81/convollama/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rb81%2Fconvollama/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28635926,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T15:01:31.228Z","status":"ssl_error","status_checked_at":"2026-01-21T14:42:58.942Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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-conversations","large-language-models","llama3","ollama","small-language-models","wizardlm2"],"created_at":"2024-09-27T04:03:16.818Z","updated_at":"2026-01-21T21:35:11.856Z","avatar_url":"https://github.com/rb81.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Deprecated](https://img.shields.io/badge/status-deprecated-red)\n\n**⚠️ DEPRECATED REPOSITORY**\nThis project is no longer actively maintained and may be out of date.\n\n---\n\n# ConvOllama\n\n![ConvOllama](/header.png)\n\nConvOllama is a Python application that facilitates AI-driven conversations using the Ollama API. It creates engaging, multi-participant discussions on user-specified topics, with the ability to assign unique profiles to each AI participant.\n\n## Features\n\n- Dynamic topic generation based on user input or keywords\n- Multi-participant conversations with AI-generated or user-defined profiles\n- User-selectable LLM models for participants\n- Configurable conversation parameters (number of participants, rounds, etc.)\n- Real-time conversation display with colorized output\n- Automatic saving of conversations in both JSON and Markdown formats\n- Graceful handling of program interruption\n- Configurable conversation history limit and logging level\n\n## Requirements\n\n- Python 3.7+\n- Ollama API access\n\n## Installation\n\n1. Clone this repository:\n   ```\n   git clone https://github.com/rb81/convollama.git\n   cd convollama\n   ```\n\n2. Install the required dependencies:\n   ```\n   pip install -r requirements.txt\n   ```\n\n3. Ensure you have Ollama set up and running on your system.\n\n## Configuration\n\nCreate a `config.yaml` file in the project root directory with the following structure:\n\n```yaml\nmoderator_model: \"wizardlm2:latest\"\nollama_host: \"http://localhost:11434\"\nsave_path: \"~/Downloads/ConvOllama\"\navailable_models:\n  - \"llama3.1:latest\"\n  - \"gemma2:latest\"\n  - \"falcon2:latest\"\nhistory_limit: 3  # Keep the last 3 rounds of messages\nlog_level: \"INFO\"  # Can be DEBUG, INFO, WARNING, ERROR, or CRITICAL\n```\n\nAdjust the values according to your preferences and setup.\n\n## Usage\n\nRun the application using the following command:\n\n```\npython main.py\n```\n\nor specify a custom configuration file:\n\n```\npython main.py -c path/to/your/config.yaml\n```\n\nYou will be guided through the following steps:\n\n1. Choose the number of participants (minimum 2)\n2. Select the LLM model for the participants\n3. Determine the conversation topic:\n   - Enter keywords and have the Moderator generate a topic\n   - Enter a discussion topic yourself\n4. For each participant:\n   - Provide a profile yourself\n   - Have the Moderator generate a profile\n   - Choose no profile\n5. Set the number of conversation rounds\n\nThe conversation will then begin. To end the conversation early, press Ctrl+C. The program will save the conversation and exit gracefully.\n\n## Output\n\nConversations are saved in two formats:\n\n1. JSON file for easy parsing and analysis\n2. Markdown file for human-readable documentation\n\nBoth files are saved in the directory specified by `save_path` in the configuration.\n\n## Model Recommendations\n\nThe Moderator works well with `wizardlm2`. Recommended Participant models include Meta's new `llama3.1`, `gemma2`, and `llama3`. You can customize the list of available models in the configuration file.\n\n## Demonstration\n\n![ConvOllama Example Conversation](/demo.png)\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Transparency Disclaimer\n\n[ai.collaboratedwith.me](https://ai.collaboratedwith.me) in creating this project.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frb81%2Fconvollama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frb81%2Fconvollama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frb81%2Fconvollama/lists"}