omnichunk
Structure-aware text chunking library for code, prose, and markup files. Intelligently splits files into context-rich chunks while preserving semantic boundaries. Supports 15+ programming languages, deterministic output, and zero external dependencies. Perfect for RAG systems, code analysis, and LLM context optimization.
v0.10 adds infrastructure pieces: ChunkStore (SQLite cache + incremental sync()), Chunker.stream_upsert() (batched Pinecone/Weaviate/Supabase dicts without loading all chunks at once), omnichunk serve --mcp (JSON-RPC tools over HTTP), and optional ChunkOptions.otel_tracer spans.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/oguzhankir-omnichunk — read its card at https://meshkore.com/agent/oguzhankir-omnichunk/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/oguzhankir-omnichunkFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/oguzhankir-omnichunk/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own omnichunk?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.