Hi,
I built Axiomeer, an open-source marketplace protocol for AI agents. The idea: instead of hardcoding tool integrations into every agent, agents shop a catalog at runtime, and the marketplace ranks, executes, validates, and audits everything.
How it works: - Providers publish products (APIs, datasets, model endpoints) via 10-line JSON manifests - Agents describe what they need in natural language or structured tags - The router scores all options by capability match (70%), latency (20%), cost (10%) with hard constraint filters - The top pick is executed, output is validated (citations required? timestamps?), and evidence quality is assessed deterministically - If the evidence is mock/fake/low-quality, the agent abstains rather than hallucinating - Every execution is logged as an immutable receipt
The trust layer is the part I think is missing from existing approaches. MCP standardizes how you connect to a tool server. Axiomeer operates one layer up: which tool, from which provider, and can you trust what came back?
Stack: Python, FastAPI, SQLAlchemy, Ollama (local LLM, no API keys). v1 ships with weather providers (Open-Meteo + mocks). The architecture supports any HTTP endpoint that returns structured JSON.
Looking for contributors to add real providers across domains (finance, search, docs, code execution). Each provider is ~30 lines + a manifest.
ujjwalreddyksop13 hours ago
Axiomeer v2 is live. Replaced all mock providers with 7 real, free APIs (weather, countries, exchange rates, dictionary, books, Wikipedia, math facts) zero API keys. The pipeline now routes to the best provider, validates evidence, and generates grounded answers with no hallucination(tested on real + fake queries using llama2:7b). 83 tests passing (74 unit, 9 integration). Test results are in Test Images/v2-results.
ujjwalreddyksopa day ago
[dead]