{"id":37298447,"url":"https://github.com/dkedar7/deepagent-code","last_synced_at":"2026-04-18T22:10:46.892Z","repository":{"id":332018323,"uuid":"1132463680","full_name":"dkedar7/deepagent-code","owner":"dkedar7","description":"A Claude Code-style CLI for running LangGraph agents from the terminal","archived":false,"fork":false,"pushed_at":"2026-02-03T05:08:47.000Z","size":489,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-03T18:38:27.772Z","etag":null,"topics":["agents","ai","claude-code","langgraph","llm"],"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/dkedar7.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":"2026-01-12T01:49:47.000Z","updated_at":"2026-02-03T05:08:50.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/dkedar7/deepagent-code","commit_stats":null,"previous_names":["dkedar7/langgraph_cli","dkedar7/deepagent-code"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/dkedar7/deepagent-code","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkedar7%2Fdeepagent-code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkedar7%2Fdeepagent-code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkedar7%2Fdeepagent-code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkedar7%2Fdeepagent-code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dkedar7","download_url":"https://codeload.github.com/dkedar7/deepagent-code/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dkedar7%2Fdeepagent-code/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31986482,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"ssl_error","status_checked_at":"2026-04-18T20:23:29.375Z","response_time":103,"last_error":"SSL_read: 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":["agents","ai","claude-code","langgraph","llm"],"created_at":"2026-01-16T02:42:23.624Z","updated_at":"2026-04-18T22:10:46.882Z","avatar_url":"https://github.com/dkedar7.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# deepagent-code\n\nA Claude Code-style CLI for running LangGraph agents from the terminal.\n\n![deepagent-code](examples/image.png)\n\n## Installation\n\n```bash\npip install deepagent-code\n```\n\nOr install directly from GitHub:\n```bash\npip install git+https://github.com/dkedar7/deepagent-code.git\n```\n\n## Quick Start\n\nRun with the default agent (requires `ANTHROPIC_API_KEY`):\n```bash\nexport ANTHROPIC_API_KEY=\"your_api_key\"\ndeepagent-code\n```\n\nOr specify your own agent:\n```bash\ndeepagent-code -a path/to/your_agent.py:graph\n```\n\nThis launches an interactive conversation loop with your agent.\n\n## Usage\n\n```bash\n# Use the default agent\ndeepagent-code\n\n# Send a message directly\ndeepagent-code \"Hello, agent!\"\n\n# Specify a custom agent file\ndeepagent-code -a my_agent.py:graph\n\n# Use a module path\ndeepagent-code -a mypackage.agents:chatbot\n\n# Read message from a file\ndeepagent-code -f ./prompt.md\n\n# Non-interactive mode (auto-approve tool calls)\ndeepagent-code --no-interactive\n\n# Verbose output\ndeepagent-code -v\n```\n\n## Commands\n\nIn the interactive loop:\n- `/q` or `/quit` - Exit\n- `/c` - Clear conversation history\n- `/h` or `/help` - Show help\n\n## Environment Variables\n\n```bash\n# Agent location (path/to/file.py:variable_name or module:variable)\nexport DEEPAGENT_SPEC=\"my_agent.py:graph\"\ndeepagent-code\n\n# Working directory\nexport DEEPAGENT_WORKSPACE_ROOT=\"/path/to/workspace\"\n\n# Stream mode (updates or values)\nexport DEEPAGENT_STREAM_MODE=\"updates\"\n```\n\n## Configuration Files\n\n`deepagent-code` reads TOML config from two locations and merges them\n(project overrides global):\n\n- **Global**: `~/.deepagents/config.toml` (shared with the upstream\n  `deepagents` CLI)\n- **Project**: `deepagents.toml` in the current directory or any ancestor\n\nPrecedence: CLI args \u003e env vars \u003e project TOML \u003e global TOML \u003e defaults.\n\nExample `deepagents.toml`:\n\n```toml\n[agent]\nspec = \"my_agent.py:graph\"\nworkspace_root = \".\"\n\n[ui]\nverbose = true\nasync_mode = false\nstream_mode = \"updates\"\n\n[configurable]\n# seeds LangGraph RunnableConfig.configurable\nthread_id = \"my-thread\"\n```\n\n## CLI Options\n\n```\nUsage: deepagent-code [OPTIONS] [MESSAGE]\n\nArguments:\n  MESSAGE  Optional input to send to the agent immediately\n\nOptions:\n  -a, --agent TEXT                Agent spec (path/to/file.py:graph or module:graph)\n  -g, --graph-name TEXT           Graph variable name (default: \"graph\")\n  -f, --file PATH                 Read message from a file (any extension)\n  --interactive/--no-interactive  Handle interrupts (default: interactive)\n  --async-mode/--sync-mode        Async streaming (default: sync)\n  --stream-mode TEXT              Stream mode (updates or values)\n  -v, --verbose                   Verbose output\n```\n\n## Creating Your Own Agent\n\nYour agent file should export a compiled LangGraph graph:\n\n```python\n# my_agent.py\nfrom deepagents import create_deep_agent\nfrom langgraph.checkpoint.memory import MemorySaver\n\nagent = create_deep_agent(\n    name=\"My Agent\",\n    model=\"anthropic:claude-sonnet-4-20250514\",\n    checkpointer=MemorySaver(),\n)\n```\n\nThen run it:\n```bash\ndeepagent-code -a my_agent.py:agent\n```\n\n## Programmatic Use\n\n```python\nfrom deepagent_code import stream_graph_updates, prepare_agent_input\n\ninput_data = prepare_agent_input(message=\"Hello!\")\n\nfor chunk in stream_graph_updates(graph, input_data):\n    if chunk.get(\"chunk\"):\n        print(chunk[\"chunk\"], end=\"\")\n```\n\n## License\n\nMIT License - see LICENSE file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkedar7%2Fdeepagent-code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdkedar7%2Fdeepagent-code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdkedar7%2Fdeepagent-code/lists"}