{"id":50175823,"url":"https://github.com/bgauryy/octocode","last_synced_at":"2026-06-03T14:00:36.769Z","repository":{"id":297531353,"uuid":"996813130","full_name":"bgauryy/octocode","owner":"bgauryy","description":"MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public \u0026 private repos based on your permissions | Transform any accessible codebase/s into AI-optimized knowledge on simple and complex flows | Find real implementations and live docs from anywhere","archived":false,"fork":false,"pushed_at":"2026-05-23T13:06:14.000Z","size":127198,"stargazers_count":845,"open_issues_count":4,"forks_count":72,"subscribers_count":5,"default_branch":"main","last_synced_at":"2026-05-23T15:08:23.633Z","etag":null,"topics":["agent","ai","ai-agents","ai-tools","claude-ai","code-intelligence","code-search","context","cursor","cursor-ai","development","github","github-api","llm","mcp","model-context-protocol","modelcontextprotocol","octocode","semantic-search","vibe-coding"],"latest_commit_sha":null,"homepage":"https://octocode.ai/","language":"TypeScript","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/bgauryy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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":"AGENTS.md","dco":null,"cla":null},"funding":{"github":["bgauryy"],"custom":["https://buymeacoffee.com/bgauryy"]}},"created_at":"2025-06-05T13:56:40.000Z","updated_at":"2026-05-23T13:06:15.000Z","dependencies_parsed_at":"2026-03-14T21:04:35.289Z","dependency_job_id":null,"html_url":"https://github.com/bgauryy/octocode","commit_stats":null,"previous_names":["bgauryy/octocode-mcp","bgauryy/octocode"],"tags_count":12,"template":false,"template_full_name":null,"purl":"pkg:github/bgauryy/octocode","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bgauryy%2Foctocode","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bgauryy%2Foctocode/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bgauryy%2Foctocode/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bgauryy%2Foctocode/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bgauryy","download_url":"https://codeload.github.com/bgauryy/octocode/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bgauryy%2Foctocode/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33867802,"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":"2026-06-03T02:00:06.370Z","response_time":59,"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":["agent","ai","ai-agents","ai-tools","claude-ai","code-intelligence","code-search","context","cursor","cursor-ai","development","github","github-api","llm","mcp","model-context-protocol","modelcontextprotocol","octocode","semantic-search","vibe-coding"],"created_at":"2026-05-25T04:00:24.762Z","updated_at":"2026-06-03T14:00:36.742Z","avatar_url":"https://github.com/bgauryy.png","language":"TypeScript","funding_links":["https://github.com/sponsors/bgauryy","https://buymeacoffee.com/bgauryy"],"categories":["TypeScript","MCP","Developer Tools"],"sub_categories":["Code Analysis"],"readme":"# Octocode: Research Driven Development for AI\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/bgauryy/octocode-mcp/raw/main/packages/octocode-mcp/assets/logo_white.png\" width=\"400px\" alt=\"Octocode Logo\"\u003e\n  \n  \u003ch3\u003eResearch like a Senior Staff Engineer.\u003cbr/\u003eIn every codebase, in seconds.\u003c/h3\u003e\n  \u003cp\u003e\u003cstrong\u003eStop guessing.\u003c/strong\u003e Octocode researches code \u003cstrong\u003elocally and externally\u003c/strong\u003e: your own workspace (ripgrep + LSP-level go-to-definition, references, call hierarchy) and the world's (GitHub repos, PRs, npm/PyPI packages), turning it into verifiable evidence your AI can search, read, and trace.\u003c/p\u003e\n  \u003cp\u003eUse it as an \u003cstrong\u003eMCP server\u003c/strong\u003e inside your AI assistant, or as a \u003cstrong\u003eterminal CLI\u003c/strong\u003e.\u003c/p\u003e\n\n  \u003cp\u003e\n    \u003ca href=\"https://octocode.ai\"\u003e\u003cstrong\u003eoctocode.ai\u003c/strong\u003e\u003c/a\u003e\n    \u0026nbsp;·\u0026nbsp;\n    \u003ca href=\"#-as-an-mcp-server\"\u003eMCP Server\u003c/a\u003e\n    \u0026nbsp;·\u0026nbsp;\n    \u003ca href=\"#-as-a-cli\"\u003eCLI\u003c/a\u003e\n    \u0026nbsp;·\u0026nbsp;\n    \u003ca href=\"#skills\"\u003eSkills\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n---\n\n## Two ways to run Octocode\n\n| | 🔌 **As an MCP Server** | 💻 **As a CLI** |\n|---|---|---|\n| **For** | Your AI assistant (Claude Code, Cursor, Claude Desktop, +13 more) | Your terminal \u0026 scripts |\n| **Install** | `npx octocode-cli install` | `brew install bgauryy/octocode/octocode` |\n| **You get** | 14 research tools wired into your agent | The same 14 tools, runnable from the shell |\n| **Best for** | Deep agent research, planning, PR review | Quick scripted lookups, CI, piping to other tools |\n\nSame engine, same tools, two surfaces. Pick one or use both.\n\n\u003e **Prerequisites**: GitHub authentication for the GitHub-backed tools. Run `octocode login`, or see [Authentication Setup](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/providers/AUTHENTICATION_SETUP.md).\n\n---\n\n## 🔌 As an MCP Server\n\nWire Octocode's tools into your AI assistant. The interactive installer handles GitHub OAuth, MCP server config, and the skills marketplace:\n\n```bash\nnpx octocode-cli install\n```\n\nPass `--ide \u003cclient\u003e` for a non-interactive install (e.g. `octocode install --ide cursor`), and `-m direct` only to point a client at a locally installed MCP binary.\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eOne-Click Install (Cursor)\u003c/strong\u003e\u003c/summary\u003e\n\n[\u003cimg src=\"https://cursor.com/deeplink/mcp-install-dark.svg\" alt=\"Install in Cursor\"\u003e](https://cursor.com/en/install-mcp?name=octocode\u0026config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyJvY3RvY29kZS1tY3BAbGF0ZXN0Il19)\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eManual MCP Configuration\u003c/strong\u003e\u003c/summary\u003e\n\nAdd to your MCP configuration file:\n\n```json\n{\n  \"mcpServers\": {\n    \"octocode\": {\n      \"command\": \"npx\",\n      \"args\": [\"octocode-mcp@latest\"]\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eResearch Skill (Direct Install)\u003c/strong\u003e\u003c/summary\u003e\n\n```bash\nnpx add-skill https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-research\n```\n\n\u003c/details\u003e\n\nThe [Octocode MCP Server](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-mcp) connects your AI assistant to code:\n\nThe [Octocode MCP Server](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-mcp) connects your AI assistant to code:\n\n- **GitHub**: Search repositories, find usage patterns, read implementations, explore PRs\n- **Local Tools**: Search code (ripgrep), browse directories, find files in your local codebase\n- **LSP Intelligence**: Go to Definition, Find References, Call Hierarchy (compiler-level understanding)\n- **Package Discovery**: Resolve npm/PyPI packages to their source repos\n\n### Benchmark Snapshot\n\nHermetic evals: **212/212 passing**. For agent research, Octocode MCP is the best default: it wins the combined benchmark with **99/105 quality** and **17,274 output tokens** on the full 60-query remote sweep (**89% less than raw `gh`**).\n\n**Token benchmark (lower is better)**\n\n| Method | Token load | Tokens | Result |\n|---|---:|---:|---|\n| raw `gh` | `████████████████████` | 153,042 | baseline |\n| Octocode CLI | `████░░░░░░░░░░░░░░░░` | 29,365 | 81% less than `gh` |\n| **Octocode MCP** | `██░░░░░░░░░░░░░░░░░░` | **17,274** | **89% less than `gh`** |\n\n**Quality benchmark (higher is better)**\n\n| Method | Quality bar | Score | Best use |\n|---|---:|---:|---|\n| **Octocode MCP** | `███████████████████░` | **99/105 · 94%** | Deep agent research + local/LSP flow |\n| Octocode CLI | `███████████████░░░░░` | 79/105 · 75% | Short scripted research |\n| raw `gh` | `not scored` | baseline | Writes and direct GitHub API access |\n\n**Token × Quality visual axis**\n\nX-axis = token savings vs raw `gh` (right is better). Y-axis = research quality score (up is better). **Best overall is the upper-right quadrant.**\n\n```text\nQuality ↑\n100 |                                                  ● Octocode MCP\n 90 |                                                    99/105 quality\n 80 |                                      ● Octocode CLI 89% token savings\n 70 |                                        79/105 quality\n 60 |\n 50 |\n 40 |\n 30 |\n 20 |\n 10 |\n  0 | ● raw gh\n    +--------------------------------------------------------------→ Token savings\n      0%               40%               80%              90%+\n      baseline                          CLI 81%        MCP 89%\n```\n\n| Point | X: token benchmark | Y: quality benchmark | Interpretation |\n|---|---:|---:|---|\n| **Octocode MCP** | 89% less than `gh` | **99/105** | Best combined token + quality result |\n| Octocode CLI | 81% less than `gh` | 79/105 | Best short/scripted structured runner |\n| raw `gh` | baseline | not scored | Direct API/writes; verbose reads |\n\n**Best-by-scenario matrix**\n\n| Scenario | Best tokens | Best quality | Recommendation |\n|---|---|---|---|\n| Full remote research sweep | **Octocode MCP** | **Octocode MCP** | Default for agent research |\n| Short one-off scripted run | **Octocode CLI** | Octocode CLI / MCP | Use CLI when MCP init is not amortized |\n| Shallow PR listing | **Octocode MCP** | **Octocode MCP** | MCP for triage |\n| PR triage with diff stats | **Octocode MCP** | **Octocode MCP** | MCP avoids `1 + N` follow-up calls |\n| Remote directory browsing | **Octocode MCP** | **Octocode MCP** | Raw `gh api /contents` is very verbose |\n| Local shallow grep/find | **Octocode local tools** | **Octocode local tools** | Octocode for evidence |\n| Local targeted code read | **Octocode local tools** | **Octocode local tools** | Use `matchString` / line ranges |\n| Local semantic flow | **Octocode MCP LSP** | **Octocode MCP LSP** | Definitions, references, call hierarchy |\n| GitHub writes | **raw `gh`** | **raw `gh`** | Octocode is read-only |\n\nLocal note: Octocode local tools win for structured evidence, metadata, targeted reads, PCRE2, and LSP (`definition`, `references`, `call hierarchy`). Octocode `verbosity:\"concise\"` is available for lossy broad probes; use compact/default for evidence. Details: [Benchmark Suite](https://github.com/bgauryy/octocode-mcp/blob/main/benchmark/github/README.md).\n\nhttps://github.com/user-attachments/assets/de8d14c0-2ead-46ed-895e-09144c9b5071\n\n---\n\n## 💻 As a CLI\n\nInstall the `octocode` command globally with [Homebrew](https://brew.sh) and run all 14 tools straight from your terminal, no MCP wiring required:\n\n```bash\nbrew install bgauryy/octocode/octocode    # → octocode v1.5.0\n```\n\n\u003e Or `brew tap bgauryy/octocode \u0026\u0026 brew install octocode` (short form), or run on demand with `npx octocode-cli`. Node is pulled in automatically. Run `octocode login` first for the GitHub-backed tools.\n\nThe CLI is both a **setup wizard** (install the MCP server + skills, manage GitHub auth, sync configs across editors) and a **standalone tool runner** (call any Octocode tool, pipe the JSON anywhere).\n\n**Commands**\n\n| Command | What it does |\n|---------|--------------|\n| `octocode install` | Configure `octocode-mcp` for an IDE/agent (`--ide \u003cclient\u003e`, `-m npx\\|direct`, `--force`, `--json`) |\n| `octocode auth` | Manage GitHub authentication (interactive menu) |\n| `octocode login` / `logout` | Sign in / out of GitHub via OAuth device flow (`--hostname` for Enterprise) |\n| `octocode status` | Octocode health: auth + installed MCPs + cache (`--sync`, `--json`) |\n| `octocode token` | Print the GitHub token using the MCP server's resolution order (`--source`, `--validate`) |\n| `octocode skills` | Search / install / remove / sync Agent Skills (`--targets`, `--mode copy\\|symlink`) |\n| `octocode mcp` | MCP marketplace: `list` / `install` / `remove` / `status` (`--id`, `--client`, `--env`) |\n| `octocode sync` | Sync MCP configs across all installed IDE clients (`--dry-run`, `--status`) |\n| `octocode cache` | Inspect / clean cloned repos, skills, logs, and tool caches |\n| `octocode tools` | List tools, show a tool's schema, or run one with `--queries '\u003cjson\u003e'` |\n| `octocode instructions` | Print MCP instructions + every tool schema |\n\nTop-level flags: `--version`/`-v`, `--help`/`-h`, `--json`/`-j`.\n\n**The 14 tools.** Run any directly with `octocode tools \u003cname\u003e --queries '\u003cjson\u003e'`:\n\n| Group | Tools |\n|-------|-------|\n| GitHub | `githubSearchCode` · `githubSearchRepositories` · `githubSearchPullRequests` · `githubGetFileContent` · `githubViewRepoStructure` · `githubCloneRepo` |\n| Local | `localSearchCode` (ripgrep) · `localFindFiles` · `localGetFileContent` · `localViewStructure` |\n| LSP | `lspGotoDefinition` · `lspFindReferences` · `lspCallHierarchy` |\n| Package | `packageSearch` (npm / PyPI → source repo) |\n\n**Quick start**\n\n```bash\noctocode login                                   # GitHub OAuth\noctocode install --ide cursor                    # wire MCP into an editor\noctocode skills install --targets claude-code    # add Agent Skills\noctocode tools                                    # list every tool\noctocode tools localSearchCode --queries '{\"path\":\".\",\"pattern\":\"fn\"}'\n```\n\nInstall targets include Cursor, Claude Code, Claude Desktop, Windsurf, Zed, Trae, Antigravity, Kiro, Codex, Opencode, Gemini CLI, Goose, and the VS Code extensions Cline / Roo / Continue. Full details: [CLI Reference](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/reference/CLI_REFERENCE.md).\n\n---\n\n## Packages\n\nThis is a yarn-workspaces monorepo. Each package has its own `README.md`; all setup/reference docs live in [`docs/`](https://github.com/bgauryy/octocode-mcp/tree/main/docs), and all AI agent guidance lives in the root [`AGENTS.md`](https://github.com/bgauryy/octocode-mcp/blob/main/AGENTS.md).\n\n| Package | Purpose |\n|---------|---------|\n| [`octocode-mcp`](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-mcp) | MCP server: 14 tools across GitHub, local FS, LSP |\n| [`octocode-cli`](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-cli) | CLI: installer, tool runner, skills marketplace |\n| [`octocode-vscode`](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-vscode) | VS Code extension: GitHub OAuth + multi-editor MCP install |\n| [`octocode-shared`](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-shared) | Shared utilities: credentials, session, platform |\n| [`octocode-security-utils`](https://github.com/bgauryy/octocode-mcp/tree/main/packages/octocode-security-utils) | Standalone security utilities |\n\n---\n\n## Skills\n\n\u003e [Agent Skills](https://agentskills.io/what-are-skills) are a lightweight, open format for extending AI agent capabilities.\n\u003e Skills index: [skills/README.md](https://github.com/bgauryy/octocode-mcp/blob/main/skills/README.md)\n\n**Research \u0026 Code Analysis**\n\n| Skill | What it does |\n|-------|--------------|\n| [**Researcher**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-researcher) | Code search \u0026 exploration: local LSP + external (GitHub, npm/PyPI) |\n| [**Research**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-research) | Multi-phase research with sessions, checkpoints, state persistence |\n| [**Engineer**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-engineer) | Understand, write, analyze, audit code: AST + LSP + dependency graph |\n| [**Brainstorming**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-brainstorming) | Idea validation grounded in evidence: GitHub, npm/PyPI, web in parallel |\n| [**News**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-news) | What's new in AI, dev tools, web platform, security, notable repos |\n\n**Planning \u0026 Writing**\n\n| Skill | What it does |\n|-------|--------------|\n| [**Plan**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-plan) | Evidence-based planning: Understand \u003e Research \u003e Plan \u003e Implement |\n| [**RFC Generator**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-rfc-generator) | Formal technical decisions with alternatives, trade-offs, and recommendations |\n| [**Doc Writer**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-documentation-writer) | 6-phase pipeline producing 16+ validated docs |\n| [**Prompt Optimizer**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-prompt-optimizer) | Turn weak prompts into enforceable agent protocols |\n| [**Agentic Flow**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/agentic-flow-best-practices) | Thinking framework for designing/reviewing MCP \u0026 multi-agent workflows |\n\n**Review \u0026 Critique**\n\n| Skill | What it does |\n|-------|--------------|\n| [**PR Reviewer**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-pull-request-reviewer) | PR \u0026 local code review across 7 domains with LSP flow tracing |\n| [**Roast**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-roast) | Brutal code critique with file:line citations and severity levels |\n\n**Build \u0026 Output**\n\n| Skill | What it does |\n|-------|--------------|\n| [**Slides**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-slides) | Polished multi-file HTML presentations via 6-phase design flow |\n| [**Design**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-design) | Dynamic DESIGN.md generator covering visual language, components, a11y |\n| [**Chrome DevTools**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-chrome-devtools) | CDP-level browser debugging: network, console, perf, DOM, screenshots |\n\n**Tooling \u0026 Setup**\n\n| Skill | What it does |\n|-------|--------------|\n| [**Install**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-install) | Interactive step-by-step Octocode installer for macOS and Windows |\n| [**CLI**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-cli) | Run Octocode MCP tools from the terminal without wiring MCP |\n| [**Search Skill**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-search-skill) | Find, evaluate, install, refactor Agent Skills (SKILL.md format) |\n| [**Stats**](https://github.com/bgauryy/octocode-mcp/tree/main/skills/octocode-stats) | Local HTML dashboard from Octocode MCP usage stats |\n\nhttps://github.com/user-attachments/assets/5b630763-2dee-4c2d-b5c1-6335396723ec\n\n---\n\n## Documentation\n\nFull index: **[docs/README.md](https://github.com/bgauryy/octocode-mcp/blob/main/docs/README.md)**. All monorepo documentation lives in [`docs/`](https://github.com/bgauryy/octocode-mcp/tree/main/docs) (no per-package `docs/`).\n\n**Docs map**\n- [`docs/configuration/`](https://github.com/bgauryy/octocode-mcp/tree/main/docs/configuration): install, auth providers, MCP clients, env/config, troubleshooting\n- [`docs/dev/`](https://github.com/bgauryy/octocode-mcp/tree/main/docs/dev): tool/API references, workflows, architecture, contributing, skills\n- [`docs/specs/`](https://github.com/bgauryy/octocode-mcp/tree/main/docs/specs): design specs and RFCs\n\n**Setup**\n- [Authentication Setup](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/providers/AUTHENTICATION_SETUP.md) · [GitHub](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/providers/GITHUB_SETUP_GUIDE.md)\n- [Configuration Reference](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/CONFIGURATION_REFERENCE.md)\n- [Using octocode-mcp with Pi](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/clients/PI_SETUP_GUIDE.md)\n\n**Tool References**\n- [GitHub Tools](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/reference/GITHUB_TOOLS_REFERENCE.md)\n- [Local + LSP Tools](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/reference/LOCAL_TOOLS_REFERENCE.md)\n- [Clone \u0026 Local Workflow](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/workflows/CLONE_AND_LOCAL_TOOLS_WORKFLOW.md)\n\n**CLI \u0026 Skills**\n- [CLI Reference](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/reference/CLI_REFERENCE.md)\n- [Skills Guide](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/SKILLS_GUIDE.md) · [Skills Index](https://github.com/bgauryy/octocode-mcp/blob/main/skills/README.md)\n- [CLI vs MCP Benchmark](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/workflows/BENCHMARK.md)\n\n**Shared Internals**\n- [Shared API Reference](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/reference/SHARED_API_REFERENCE.md) · [Credentials Architecture](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/architecture/CREDENTIALS_ARCHITECTURE.md) · [Session Persistence](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/architecture/SESSION_PERSISTENCE.md)\n\n**Operations**\n- [Troubleshooting](https://github.com/bgauryy/octocode-mcp/blob/main/docs/configuration/TROUBLESHOOTING.md) · [Development Guide](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/DEVELOPMENT_GUIDE.md) · [Agent Guidance (AGENTS.md)](https://github.com/bgauryy/octocode-mcp/blob/main/AGENTS.md)\n\n### The Manifest\n\n**\"Code is Truth, but Context is the Map.\"** Read the [Manifest for Research Driven Development](https://github.com/bgauryy/octocode-mcp/blob/main/MANIFEST.md) to understand the philosophy behind Octocode.\n\n---\n\n### Contributing\n\nSee the [Development Guide](https://github.com/bgauryy/octocode-mcp/blob/main/docs/dev/DEVELOPMENT_GUIDE.md) for monorepo setup, testing, and contribution guidelines.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n  \u003csub\u003eBuilt with care for the AI Engineering Community\u003c/sub\u003e\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbgauryy%2Foctocode","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbgauryy%2Foctocode","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbgauryy%2Foctocode/lists"}