Sep 2025 — Present
VisvoAI
- Problem
- Every team building AI agents ends up rebuilding the same layer around the model: separate integrations for each provider, system changes whenever a new model arrives, and agent logic that gets harder to extend with every new tool, prompt and approval step.
- Solution
- Two open-source Python packages that handle that layer once: visvoai-ai turns one id string into a streaming model across Gemini, Anthropic and OpenAI-compatible APIs, with a live model registry and cost metering, and visvoai-core is a lean LangGraph agent loop that products extend through hooks instead of forking. A terminal coding agent and a multi-user reference platform both run on them unmodified.
PythonLangGraphLangChainFastAPINext.jsTextualMCPRAGWeaviateRedisPostgreSQL
- 01Model layervisvoai-ai · one id string to any provider, live registry, cost metering
- 02Agent runtimevisvoai-core · LangGraph loop, step cap, override hooks
- 03Tool retrievalvisvoai-core · BM25 or hybrid search for large tool sets
- 04ProductsTerminal coding agent · multi-user reference platform
Open-source packages (visvoai-ai, visvoai-core)
- visvoai-ai: pass one id like gemini:gemini-2.5-flash and get a streaming LangChain model, across Gemini, Anthropic and any OpenAI-compatible endpoint (OpenAI, Together, Groq, OpenRouter built in).
Show 4 moreShow less
- A live model registry (price, context window, capabilities, thinking levels): 44 built-in models, extendable to about 4,000 from models.dev with an offline fallback, plus cost_of and usage_from for metering and one 4-level thinking scale over 8 provider mechanisms.
- visvoai-core: a LangGraph agent loop with a soft step cap that forces a clean final answer, 8 runtime hooks to extend nodes, routing, state and checkpointing without forking, and lifecycle persistence hooks.
- One tool contract that mixes plain typed functions, class-based tools and LangChain tools in a list, plus per-round BM25 + embedding tool retrieval for large tool sets.
- CI enforces the boundary between the public packages and the private platform; 104 + 42 tests, MIT, Python 3.11+.
Terminal coding agent (visvoai-cli)
- A terminal coding agent (Textual UI) built on the two packages, unmodified, and the reference for how far they go; 607 tests.
Show 3 moreShow less
- Shell commands are sorted into read or write: reads run without prompts inside a no-write OS sandbox (macOS sandbox-exec, Linux bubblewrap), and changes go through an approval gate with three modes and path confinement.
- Subagents run in parallel with isolated context, live logs and per-run cost traces, alongside on-demand skills and MCP servers; anything a cloned repo defines stays off until you approve it.
- Each tool batch and turn is snapshotted to a shadow git repo, so /rewind restores the code, the conversation or both to before any earlier question.
Reference platform (private, multi-user agent harness)
- Dynamic tool binding so agents stop loading every tool, which took ~57% of a typical 46k-token prompt: a small core is always bound and the rest are retrieved per step, with Gemini-embedded MCP tools.
Show 8 moreShow less
- Rewrote tool descriptions to lift recall@8 from 91% to 97% on a 211-case benchmark over 35 internal tools; a later run over 38 internal and 73 MCP tools reached 100% recall@8 with hybrid retrieval.
- Agent harness and loop on LangGraph: parallel tool batches, repeat-call blocking, schema-guided recovery from bad arguments, step caps and context compaction.
- ~40 built-in tools with role-scoped availability and resource access checks, plus human-in-the-loop approvals (approve, edit, approve-all, reject) that pause and resume the agent.
- User-defined agents, 17 on-demand skills, and subagents with isolated context, depth caps and parallel runs that stream live to the parent's UI.
- An MCP client and OAuth connectors written from scratch (Google, Microsoft, Slack, Notion, HubSpot) that sync server tools by content hash, repair malformed arguments and move large results to files.
- RAG over a per-user document library: PDF/DOCX/PPTX parsing, heading-aware chunking, Gemini embeddings and hybrid BM25 + vector search in Weaviate with citations, plus long-term memory.
- Versioned artifacts that agents and users co-edit with conflict checks, SQL over spreadsheets in DuckDB, and a network-isolated sandbox for running code.
- Per-user data isolation and encrypted per-user API keys, LLM cost and token tracking with a trace viewer, automatic audit logs, conversation branching, and stream resume over Redis Streams.
