{"data":{"slug":"sentdex-termgpt","name":"TermGPT","tagline":"Giving LLMs like GPT-4 the ability to plan and execute terminal commands","github_url":"https://github.com/Sentdex/TermGPT","owner":"Sentdex","repo":"TermGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/5905296?v=4","primary_language":"Jupyter Notebook","stars":412,"forks":95,"topics":[],"archived":false,"github_pushed_at":"2023-07-20T07:07:48+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/sentdex-termgpt","markdown_url":"https://www.graphcanon.com/tools/sentdex-termgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sentdex-termgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sentdex-termgpt","description":"Giving LLMs like GPT-4 the ability to plan and execute terminal commands","homepage_url":null,"license":"MIT","open_issues":7,"watchers":16,"ai_summary":"Sentdex/TermGPT is a project focused on enabling large language models such as GPT-4 to understand, plan, and execute terminal-based tasks.","readme_excerpt":"# TermGPT\nGiving LLMs like GPT-4 the ability to plan and execute terminal commands\n\nVideo explanation and usage examples: https://youtu.be/O4EmRi0_CI4\n\nThe notebook also breaks down how the script works.\n\n# Usage\n\nRun with `$ python3 TermGPT.py`\nYou will need to create a `.env` file similar to https://github.com/Sentdex/TermGPT/blob/main/.env.example, or set `OPENAI_API_KEY` manually.\n\nFrom here, you make your programming/development request. The script will run and query GPT-4 for a series of terminal commands to run to achieve this objective. This is including, but not limited to: reading files, writing code, reading websites, running code, running terminal commands...etc. \n\nThe proposed commands are stored to a list and then presented back to the user again in bold red text, prior to running. After reviewing these commands, you can opt to run them, or not.\n\n# Future work\n\n- I would like to primarily find an open source model that can yield similar performance to GPT-4 in this realm.\n- Simplify and add more natural language. Most likely, starting \"prompts\" will need higher and lower level understanding. Rather than doing something like --r [FILENAME], I would like to have a higher level pass via the LLM to determine if any files should be read, allowing for a pure \"natural language\" approach, along with likely far more generalization.","github_created_at":"2023-06-03T16:39:05+00:00","created_at":"2026-07-11T10:54:09.50973+00:00","updated_at":"2026-09-20T05:32:19.686186+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"language-models","name":"language models"},{"slug":"task-execution","name":"task execution"},{"slug":"terminal-commands","name":"terminal commands"}],"trust":{"provenance":{"is_fork":false,"github_id":649059972,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-15T18:01:04.744Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1122,"last_release_at":null,"stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:54:10.641Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-15T18:01:05.232Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-08-15T18:01:05.232Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-15T18:01:05.232Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Integration with large language models is required for full use of TermGPT capabilities."],"min_ram_gb":8},"constraints":{"min_ram_gb":8},"when_to_use":["- When you are working with a Jupyter Notebook environment where integrating terminal command execution into your AI workflow would be beneficial.","- If you need to augment the capabilities of large language models like GPT-4 specifically for tasks that involve planning or executing commands in a terminal setting."],"when_not_to_use":["- When your project's primary focus is not on enhancing a model’s interaction with terminal commands, but rather on other functionalities such as speech recognition.","- If you're working within an environment where Jupyter Notebook integration isn’t feasible or desirable, and your workflow requires strictly code-based or GUI interfaces."],"source":"enrich:decision_facts","observed_at":"2026-07-12T13:38:11.762Z"},"constraint_facets":{"min_ram_gb":8},"decision_summary":[{"label":"Requirements","value":"Min 8 GB RAM; Integration with large language models is required for full use of TermGPT capabilities."},{"label":"Adopt for","value":"TermGPT is designed for developers looking to enhance large language models' capability to handle terminal-based tasks by enabling them to understand, plan, and execute such operations."}]}}