Tara Menon 59ef28ffab 🔧 Fix tool calling + capability awareness
Three fixes:
1. OllamaProvider now sends tools[] in native /api/chat requests
2. OllamaProvider parses tool_calls from response (OpenAI-compatible
   format with function.name, function.arguments)
3. System prompt now lists available tools so LLM knows it can use
   bash, curl, read/write files — stops saying "I cannot do that"
2026-06-11 22:55:19 +05:30
2026-06-11 22:55:19 +05:30
2026-06-11 22:05:02 +05:30
2026-06-11 22:05:02 +05:30

GyanDoot v2.0 — AI Agent Platform

A next-generation AI Agent Platform rewritten in Rust for performance, safety, and extensibility.

Architecture

gyandoot-core        — Shared types, config, error types
gyandoot-agent       — Core agent loop, tool execution, context compression
gyandoot-providers   — LLM provider abstraction (OpenAI, Anthropic, Ollama)
gyandoot-memory      — MemPalace persistent memory system
gyandoot-platform    — Platform adapters (Telegram, Discord, Webhook, CLI)
gyandoot-security    — Credential vault, encryption, threat detection
gyandoot-kanban      — Kanban task system (decomposition, swarm, diagnostics)
gyandoot-subagents   — Sub-agent spawning and orchestration
gyandoot-skills      — Skills system (discovery, loading, preprocessing, bundles)
gyandoot-profile     — Multi-agent profile manager
gyandoot-gateway     — Gateway for platform sessions, routing, streaming

Quick Start

./install.sh
gyandoot --help

License

MIT

Description
GyanDoot v2.0 — AI Agent Platform built in Rust. Blazing fast, single binary, anti-reverse-engineered, cross-platform.
Readme 5 MiB
Languages
Rust 84.4%
JavaScript 9.1%
Shell 4.9%
PowerShell 0.8%
Batchfile 0.6%
Other 0.2%