{"id":50750471,"url":"https://github.com/agentlas-ai/hephaestus","last_synced_at":"2026-06-14T03:02:00.964Z","repository":{"id":362433002,"uuid":"1258962324","full_name":"agentlas-ai/Hephaestus","owner":"agentlas-ai","description":"No-code AI agent builder — turn one sentence into a single agent or a multi-agent team. The engine inside Agentlas. A no-code CrewAI / LangGraph / AutoGen alternative that runs on Claude Code, Codex, and Cursor.","archived":false,"fork":false,"pushed_at":"2026-06-10T23:40:02.000Z","size":2211,"stargazers_count":50,"open_issues_count":0,"forks_count":11,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-11T01:21:12.556Z","etag":null,"topics":["agent-framework","agentic-ai","ai-agent-builder","ai-agents","autogen","claude-code","crewai-alternative","langgraph","llm","meta-agent","multi-agent","no-code"],"latest_commit_sha":null,"homepage":"https://agentlas.cloud/models/hephaestus","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/agentlas-ai.png","metadata":{"files":{"readme":"README.hi.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","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}},"created_at":"2026-06-04T04:33:26.000Z","updated_at":"2026-06-10T23:40:07.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/agentlas-ai/Hephaestus","commit_stats":null,"previous_names":["jeongmk522-netizen/agent_agentlas_core_engine_meta_agent","agentlas-ai/hephaestus"],"tags_count":21,"template":false,"template_full_name":null,"purl":"pkg:github/agentlas-ai/Hephaestus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlas-ai%2FHephaestus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlas-ai%2FHephaestus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlas-ai%2FHephaestus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlas-ai%2FHephaestus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/agentlas-ai","download_url":"https://codeload.github.com/agentlas-ai/Hephaestus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/agentlas-ai%2FHephaestus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34307685,"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":"2026-06-14T02:00:07.365Z","response_time":62,"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-framework","agentic-ai","ai-agent-builder","ai-agents","autogen","claude-code","crewai-alternative","langgraph","llm","meta-agent","multi-agent","no-code"],"created_at":"2026-06-11T01:01:06.110Z","updated_at":"2026-06-14T03:02:00.958Z","avatar_url":"https://github.com/agentlas-ai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://agentlas.cloud\"\u003e\n    \u003cimg src=\"assets/agentlas-agent-lab-banner.svg\" alt=\"Agentlas Agent Lab banner\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eHephaestus\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eएक अधूरा agent idea लेकर उसे installable Agentlas agent/team repository में बदलें।\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  एक specialist agent बनाएं, multi-agent team तैयार करें, या किसी मौजूदा Claude/Codex/OpenClaw/Hermes workspace को public-safe Agentlas package में बदलें।\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"README.md\"\u003eEnglish\u003c/a\u003e\n  ·\n  \u003ca href=\"README.ko.md\"\u003e한국어\u003c/a\u003e\n  ·\n  \u003ca href=\"README.zh-CN.md\"\u003e中文\u003c/a\u003e\n  ·\n  \u003ca href=\"README.ja.md\"\u003e日本語\u003c/a\u003e\n  ·\n  \u003ca href=\"README.hi.md\"\u003eहिन्दी\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/agentlas-meta-agent-architecture.svg\" alt=\"Agentlas Meta-Agent architecture decomposition\"\u003e\n\u003c/p\u003e\n\n---\n\n## पेस्ट करके install (अपने AI से करवाएं)\n\nTerminal नया लगता है? खुद कुछ चलाने की ज़रूरत नहीं। कोई भी AI coding tool —\n**Claude Code, Codex, Gemini CLI, Antigravity, या Cursor** — खोलें और नीचे का\nmessage उसके chat box में जैसा है वैसा paste करें। Agent आपके लिए installer\nचलाएगा और अगली command बता देगा:\n\n```text\nइस workspace में Hephaestus Agentlas meta-agent set up करो। Terminal में\n`curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/v0.3.0/scripts/install-all-runtimes.sh | bash`\nचलाओ, फिर बताओ कि मैं जो tool इस्तेमाल कर रहा/रही हूँ (Claude Code, Codex,\nGemini CLI, Antigravity, Cursor) उसमें सही /hephaestus command क्या है। कुछ\nfail हो तो error पढ़कर ठीक करो और दोबारा try करो।\n```\n\nखत्म होने पर अपने tool में `/hephaestus` type करें। खुद commands चलाना चाहते\nहैं? नीचे दिया **Quickstart** इस्तेमाल करें।\n\n---\n\n## Quickstart\n\nतीन install paths हैं। अगर आपको पूरा Agentlas runtime चाहिए, तो **1 + 3** इस्तेमाल करें। अगर यह package सीधे Claude Code, Codex या किसी सामान्य project folder में चाहिए, तो **2** इस्तेमाल करें।\n\n| Path | कब इस्तेमाल करें | क्या खोलना है |\n|---|---|---|\n| 1. Agentlas Terminal | shell से Agentlas agents चलाने के लिए | पहले Agentlas Desktop, फिर macOS Terminal / Windows PowerShell / Linux terminal |\n| 2. Standalone Hephaestus | Claude Code, Codex या normal repo में direct install के लिए | Claude Code, Codex या OS terminal |\n| 3. Agentlas Desktop | visual local runtime, agent/team management, vault, Apps के लिए | browser में download page, फिर Agentlas Desktop app |\n\n### 1. Agentlas Terminal install करें\n\nAgentlas Terminal **Agentlas Desktop** से install होता है। पहले Desktop install करें, फिर app में यह खोलें:\n\n```text\nAgentlas Desktop -\u003e Settings -\u003e Use from the terminal (`agentlas` CLI) -\u003e Install CLI\n```\n\nउसके बाद अपना सामान्य terminal खोलें और `agentlas` चलाएं।\n\n**macOS Terminal**\n\n```bash\narch=$([ \"$(uname -m)\" = \"arm64\" ] \u0026\u0026 echo arm64 || echo x64)\ncurl -fL \"https://agentlas.cloud/api/desktop/download?arch=${arch}\" -o Agentlas.dmg\nopen Agentlas.dmg\n```\n\n**Windows PowerShell**\n\n```powershell\n$r = Invoke-RestMethod https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest\n$u = ($r.assets | Where-Object { $_.name -like '*Windows-x64-Setup.exe' }).browser_download_url\nInvoke-WebRequest $u -OutFile \"$env:TEMP\\AgentlasSetup.exe\"\nStart-Process \"$env:TEMP\\AgentlasSetup.exe\"\n```\n\n**Linux terminal, AppImage**\n\n```bash\nurl=$(curl -fsSL https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest \\\n  | grep -o 'https://[^\"]*Linux-x64\\.AppImage' | head -1)\ncurl -fL \"$url\" -o Agentlas.AppImage\nchmod +x Agentlas.AppImage\n./Agentlas.AppImage\n```\n\n**Linux terminal, Debian/Ubuntu**\n\n```bash\nurl=$(curl -fsSL https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest \\\n  | grep -o 'https://[^\"]*Linux-x64\\.deb' | head -1)\ncurl -fL \"$url\" -o agentlas.deb\nsudo dpkg -i agentlas.deb\n```\n\nDesktop Settings से CLI install करने के बाद:\n\n```bash\nagentlas list\nagentlas run agentlas-meta-agent \"Package this workflow for Agentlas\"\n```\n\n### 2. Hephaestus standalone install करें\n\n#### Simple file install\n\nजिस project folder में package files चाहिए, वहां macOS Terminal, Linux terminal, Windows Git Bash या WSL खोलें:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/v0.3.0/scripts/install.sh | bash\nscripts/verify-package.sh\nscripts/public_safety_check.sh\n```\n\nWindows PowerShell:\n\n```powershell\n$zip = \"$env:TEMP\\hephaestus-v0.3.0.zip\"\n$extract = \"$env:TEMP\\hephaestus-v0.3.0\"\nInvoke-WebRequest \"https://github.com/agentlas-ai/Hephaestus/archive/refs/tags/v0.3.0.zip\" -OutFile $zip\nRemove-Item $extract -Recurse -Force -ErrorAction SilentlyContinue\nExpand-Archive $zip -DestinationPath $extract -Force\n$src = Get-ChildItem $extract -Directory | Select-Object -First 1\nGet-ChildItem $src.FullName -Force | Copy-Item -Destination (Get-Location) -Recurse -Force\n```\n\n#### Claude Code plugin install\n\nMarketplace registration और plugin installation अलग steps हैं। marketplace command Claude Code को बताता है कि यह repo कहां है। install command असल plugin install करता है। install के बाद reload करें।\n\n**Claude Code chat के अंदर टाइप करें**:\n\n```text\n/plugin marketplace add https://github.com/agentlas-ai/Hephaestus --sparse .claude-plugin claude/plugins\n/plugin install hephaestus@agentlas-core-engine\n/reload-plugins\n/plugin list\n```\n\n**`claude` CLI वाले OS terminal में टाइप करें**:\n\n```bash\nclaude plugin marketplace add https://github.com/agentlas-ai/Hephaestus --sparse .claude-plugin claude/plugins\nclaude plugin install hephaestus@agentlas-core-engine\n```\n\nExpected result:\n\n```text\n✓ Installed hephaestus. Run /reload-plugins to apply.\nReloaded: 1 plugin · 0 skills · 9 agents · 0 hooks · 0 plugin MCP servers · 0 plugin LSP servers\n```\n\n#### Codex plugin install\n\nCodex chat के अंदर `/plugin marketplace add` इस्तेमाल न करें। Codex app में installed plugins देखने के लिए `/plugins` है; install OS terminal से करें।\n\n**`codex` CLI वाले OS terminal में टाइप करें**:\n\n```bash\ncodex plugin marketplace add agentlas-ai/Hephaestus --ref v0.3.0\ncodex plugin list\ncodex plugin add hephaestus@agentlas-core-engine\ncodex plugin list\n```\n\nअगर Codex session पहले से खुला है, तो नया session शुरू करें और `/plugins` से plugin दिख रहा है या नहीं देखें। Install के बाद `/hephaestus ontology` चलाएं।\n\n### 3. Agentlas Desktop install करें\n\nbrowser में खोलें:\n\n```text\nhttps://agentlas.cloud/desktop\n```\n\nDesktop आपको visual Agentlas surface देता है: local projects, agents, teams, Apps, vault references, runtime selection, built-in Core Engine Meta-Agent routing और `agentlas` CLI installer।\n\n## तस्वीरों के साथ install guide\n\nअगर आप Claude Code chat के अंदर हैं, तो Claude slash command वाली तस्वीर follow करें। Codex पहले OS terminal से install करें; Codex app में `/plugins` से installed plugins देखें। अगर आपने macOS Terminal, Windows PowerShell, Linux terminal, Git Bash या WSL खोला है, तो CLI वाली तस्वीरें follow करें।\n\n### Claude Code chat\n\nइन commands को सीधे Claude Code में type करें।\n\n![Claude Code chat install flow](assets/install-claude-code-chat.svg)\n\n### OS terminal में Claude CLI\n\nजब आपके shell में `claude` command उपलब्ध हो, तो यह path इस्तेमाल करें।\n\n![Claude CLI install flow](assets/install-claude-cli.svg)\n\n### Codex app plugin browser\n\nOS terminal में `codex plugin ...` install पूरा करने के बाद Codex app में `/plugins` type करके check करें।\n\n![Codex app plugin browser](assets/install-codex-chat.svg)\n\n### Codex Desktop या IDE Extension\n\nजब Codex में Plugins settings screen दिखे, तो यह path इस्तेमाल करें।\n\n![Codex Desktop settings install flow](assets/install-codex-desktop-settings.svg)\n\n### OS terminal में Codex CLI\n\nजब आपके shell में `codex` command उपलब्ध हो, तो यह path इस्तेमाल करें।\n\n![Codex CLI install flow](assets/install-codex-cli.svg)\n\n## क्या खोलें और कहां type करें\n\n| काम | क्या खोलें | कहां type करें |\n|---|---|---|\n| Desktop download | Browser | `https://agentlas.cloud/desktop` या OS download command |\n| `agentlas` CLI install | Agentlas Desktop | Settings -\u003e Use from the terminal -\u003e Install CLI |\n| Agentlas Terminal चलाना | OS terminal | `agentlas list`, `agentlas run ...` |\n| Claude plugin slash command से install | Claude Code | `/plugin marketplace add ...`, `/plugin install ...`, `/reload-plugins` |\n| Claude plugin shell से install | OS terminal | `claude plugin marketplace add ...`, `claude plugin install ...` |\n| Installed Codex plugins देखना | Codex app | `/plugins` |\n| Codex plugin shell से install | OS terminal | `codex plugin marketplace add ...`, `codex plugin add ...` |\n\n## यह क्या बनाता है\n\nHephaestus सिर्फ prompt answer नहीं बनाता। यह ऐसा repository छोड़ता है जिसे दूसरा runtime inspect, install, verify और आगे improve कर सके।\n\n| आप क्या मांगते हैं | Route | Output |\n|---|---|---|\n| \"X करने वाला एक agent बनाओ\" | `10-single-agent-builder` | skills, memory contracts, runtime adapters और verification वाला single worker |\n| \"इस workflow के लिए team/company बनाओ\" | `20-multi-agent-team-builder` | HQ, PM Soul, Memory Curator, Policy Gate, eval, QA और handoff वाली multi-agent team |\n| \"इस existing agent/repo/workspace को package करो\" | `30-agentlas-packager` | Desktop import, terminal, Codex, Claude, Gemini या public GitHub release के लिए साफ Agentlas package |\n\n## v0.3.0 में नया\n\n- **CJK search काम करता है।** tokenizer अब Korean/Japanese/Chinese runs के लिए character bigrams बनाता है और FTS index `trigram` tokenizer इस्तेमाल करता है — zero-install CJK corpus search। मौजूदा databases पहली बार खुलने पर अपने आप re-index होते हैं।\n- **RRF hybrid ranking।** full-text और vector rankings fixed weights की जगह Reciprocal Rank Fusion से जुड़ती हैं, bounded candidate pool के साथ।\n- **Host-LLM search hooks (optional, zero cost)।** Claude Code / Codex जैसे host runtimes query-expansion और rerank hooks inject कर सकते हैं; embedding API की ज़रूरत नहीं, और private/confidential chunks कभी cloud hooks तक नहीं जाते।\n- **Ontology-backed agent mode।** builders retrieval-first, citation-attached agents बनाते हैं (`modes/ontology-backed-agent.md`, reference: `examples/ontology-proposal-agent/`); contracts rule-based inject होते हैं और `loop_policy` task risk से तय होता है।\n- **Adapter drift gate + MCP surface check।** `scripts/sync-adapters.sh --check` और `scripts/verify-mcp-surface.sh` जोड़े गए।\n\n## Architecture\n\npublic core architecture/foldering contract है। Claude, Codex, Gemini, Desktop और Terminal folders उसी core पर बने thin adapters हैं; वे अलग source of truth नहीं हैं।\n\n| Public contract | काम |\n|---|---|\n| Mode auto-detection | generation से पहले `single-agent-creator`, `team-builder`, या `agentlas-packager` चुनता है |\n| Clarify question loop | सिर्फ runtime, public/private boundary, tools या safety पर असर डालने वाले सवाल पूछता है |\n| `.agentlas` auto-activation | local runtime को project memory, sitemap/task-bias, Memory Tickets और vault references seed करने देता है |\n| Skill lifecycle registry | skill को candidate metadata से शुरू करता है और trial/Curator decision ledgers रखता है |\n\nDefault export conservative है। Generated skills automatic first-class recall नहीं बनते। Curator को execution evidence, sealed holdout/replay, rollback coverage और workspace policy approval देखना होगा।\n\n## Agentlas Desktop और Terminal साथ क्यों बेहतर हैं\n\n- Desktop agent/team structure, local projects, Apps, vault references और runtime choices दिखाता है।\n- Terminal वही package `agentlas` command से चलाता है।\n- Desktop/Terminal में Core Engine Meta-Agent path built in है, इसलिए fresh install के बाद भी agent creation और packaging शुरू हो सकती है।\n- Standalone Claude/Codex install तब उपयोगी है जब package सीधे उन runtimes में चाहिए।\n\n## Compare\n\n| तुलना | उनकी ताकत | Hephaestus क्या जोड़ता है |\n|---|---|---|\n| OpenAI / Codex | strong models और coding terminal | portable repo contracts, `.agentlas` memory/package files, skills, schemas, runtime adapters, public verification |\n| Claude / Claude Code | strong reasoning और Claude-native workflows | Claude support, लेकिन Claude-only नहीं; Codex, Gemini, Desktop, terminal और `AGENTS.md` भी aligned रहते हैं |\n| OpenClaw | local identity और workspace agent loop | visible role folders, Agentlas package contracts, public-safety checks, Desktop import, vault references |\n| Hermes | persona और memory-centered local runtime | PM Soul, Memory Tickets, sitemap/task-bias, policy/eval/QA, skill lifecycle evidence |\n\nOpenAI और Claude model/runtime surfaces हैं। OpenClaw और Hermes local-agent experiences हैं। Hephaestus agent को portable, inspectable, installable और publishable बनाने वाली package layer है।\n\n## Usage examples\n\n```text\n/meta-agent Create a research agent for SEC filing analysis.\nPackage it for Codex, Claude Code, Gemini, and Agentlas Desktop.\n```\n\n```text\nUse Hephaestus.\nBuild a customer-support operations team with PM Soul, Memory Curator, Policy Gate, QA, eval, and public-safe release checks.\n```\n\n```text\nPackage this local OpenClaw/Hermes-style workspace into Agentlas architecture.\nKeep private notes, machine paths, raw logs, and secrets out of the public repo.\n```\n\n## Docs\n\n| Goal | Document |\n|---|---|\n| canonical route समझना | [`AGENTS.md`](AGENTS.md) |\n| team contract देखना | [`agent.md`](agent.md) |\n| source of truth देखना | [`docs/source-of-truth.md`](docs/source-of-truth.md) |\n| runtime boundaries समझना | [`docs/runtime-sync-boundaries.md`](docs/runtime-sync-boundaries.md) |\n| mode चुनना | [`docs/mode-classifier.md`](docs/mode-classifier.md) |\n| package verify करना | [`scripts/verify-package.sh`](scripts/verify-package.sh) |\n| public safety check करना | [`scripts/public_safety_check.sh`](scripts/public_safety_check.sh) |\n\n## Public Safety Boundary\n\nयह repo hosted Agentlas billing/account logic, production credentials, customer data, raw private logs, raw transcripts, desktop keychain storage, local database implementation या private deployment configuration शामिल नहीं करता।\n\nPublic package में local machine paths, API keys, tokens, private keys, service-account JSON, `.env` secrets, private research notes, raw chat transcripts, customer logs, hosted billing/account/OAuth internals या desktop storage internals नहीं होने चाहिए।\n\n## License\n\nApache-2.0. [`LICENSE`](LICENSE) देखें।\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentlas-ai%2Fhephaestus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagentlas-ai%2Fhephaestus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagentlas-ai%2Fhephaestus/lists"}