{"id":50565552,"url":"https://github.com/graphlit/skills","last_synced_at":"2026-06-04T14:30:21.424Z","repository":{"id":361985688,"uuid":"1256649176","full_name":"graphlit/skills","owner":"graphlit","description":null,"archived":false,"fork":false,"pushed_at":"2026-06-02T04:23:52.000Z","size":95,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-02T06:05:22.405Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"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/graphlit.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-02T01:15:11.000Z","updated_at":"2026-06-02T04:23:56.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/graphlit/skills","commit_stats":null,"previous_names":["graphlit/skills"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/graphlit/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphlit%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphlit%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphlit%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphlit%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/graphlit","download_url":"https://codeload.github.com/graphlit/skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphlit%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33910136,"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":"2026-06-04T02:00:06.755Z","response_time":64,"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":[],"created_at":"2026-06-04T14:30:20.604Z","updated_at":"2026-06-04T14:30:21.419Z","avatar_url":"https://github.com/graphlit.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Graphlit Skills\n\nBuild grounded chat, synced knowledge bases, and graph-aware applications with Graphlit.\n\nGraphlit is the context layer for AI applications and agents. This repo gives developers and coding agents the canonical Graphlit path: ingest or sync content, wait for processing, retrieve explicit evidence, and stream grounded answers with `streamAgent()`.\n\n[Use the Skill](skills/graphlit/SKILL.md) · [Run the Example](examples/nextjs-streaming-chat) · [Read the Docs](https://docs.graphlit.dev) · [Open Graphlit Studio](https://www.graphlit.dev)\n\n## Why This Repo Exists\n\nWhen a developer asks an agent to \"add Graphlit\", the result should use Graphlit primitives instead of drifting into generic RAG scaffolding.\n\nThis repo provides:\n\n- a reusable `graphlit` skill that routes the agent to the right Graphlit references\n- a minimal Next.js example that proves the modern Graphlit app shape\n- task-specific implementation guides for ingestion, retrieval, collections, feeds, specifications, and knowledge graph workflows\n\n## What You Can Build\n\n- grounded chat over documents, websites, notes, transcripts, and synced external content\n- customer-scoped or workspace-scoped assistants using collections\n- continuously synced knowledge bases from Slack, Google Drive, email, RSS, S3, and web crawls\n- graph-aware applications that extract entities and relationships during ingest\n\n## Canonical Graphlit Path\n\n1. Verify credentials with `getProject()`.\n2. Ingest content with `ingestUri()` or sync a source with `createFeed()`.\n3. Wait for `isContentDone()` or `isFeedDone()` before retrieval depends on new content.\n4. Scope retrieval with a collection when the app has a clear dataset, tenant, customer, project, or workspace boundary.\n5. Use `streamAgent()` as the chat harness.\n6. Keep retrieval explicit through a standalone `retrieve_contents` tool backed by `retrieveSources()` and `lookupContents()`.\n7. Return and render visible sources in the UI.\n\n## What You Get In This Repo\n\n### `skills/graphlit/`\n\nThe reusable Graphlit skill and its task-specific references. Start with [SKILL.md](skills/graphlit/SKILL.md) when the goal is to integrate Graphlit into an application or have a coding agent do it correctly.\n\n### `examples/nextjs-streaming-chat/`\n\nThe canonical sample app for this repo. It shows:\n\n- URL ingestion with `ingestUri()`\n- readiness polling with `isContentDone()`\n- collection-scoped retrieval\n- `streamAgent()` with a standalone `retrieve_contents` tool\n- streamed answers with visible sources\n\n### `drafts/`\n\nWorking drafts that can be adapted into docs, examples, or longer-form content later.\n\n## Get Started\n\n### New to Graphlit?\n\n1. Open [Graphlit Studio](https://www.graphlit.dev).\n2. Create your account, organization, and first project.\n3. Select that project so its project card is visible.\n4. Choose the target environment tab, usually `Preview` or `Production`.\n5. Click `Copy Environment Variables`.\n6. Paste the copied values into `.env.local`.\n7. Add `OPENAI_API_KEY` for the streaming example.\n\n### Run the Example\n\n```bash\ncd examples/nextjs-streaming-chat\nnpm install\ncp .env.example .env.local\nnpm run check\nnpm run dev\n```\n\nOpen `http://localhost:3000`.\n\n## Success Looks Like\n\n- the app connects to the intended Graphlit project\n- a URL ingests successfully\n- retrieval waits for content readiness\n- the agent calls `retrieve_contents`\n- the answer streams incrementally\n- the UI shows the supporting sources\n\n## Design Principles\n\n- prefer Graphlit SDK primitives over generic RAG stacks\n- keep retrieval explicit and inspectable\n- do not rely on newly ingested or newly synced content until Graphlit says it is ready\n- keep examples small enough to copy into real apps quickly\n\nThe goal is to make Graphlit easy to adopt without hiding how Graphlit actually works.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraphlit%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgraphlit%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraphlit%2Fskills/lists"}