jazzymc/xtrm-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4 Commits 1 Branch 0 Tags
872ed24f0c28dd74595d9794215a2803b2e02465
Commit Graph

4 Commits

Author SHA1 Message Date
Kaloyan Danchev
872ed24f0c Add performance features: caching, cost tracking, retry, compaction, classification, scrubbing 
Inspired by zeroclaw's lightweight patterns for slow hardware:
- Response cache (SQLite + SHA-256 keyed) to skip redundant LLM calls
- History compaction — LLM-summarize old messages when history exceeds 50
- Query classifier routes simple/research queries to cheaper models
- Credential scrubbing removes secrets from tool output before sending to LLM
- Cost tracker with daily/monthly budget enforcement (SQLite)
- Resilient provider with retry + exponential backoff + fallback provider
- Approval engine gains session "always allow" and audit log

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 09:20:52 +02:00
Kaloyan Danchev
e24e3026b6 Add Discord attachment reading and web search capabilities 
- Discord channel now downloads and extracts text from attachments (text files, PDFs)
- Added WebSearchTool using DuckDuckGo for researcher and coder agents
- Improved WebFetchTool with User-Agent header and HTML-to-text stripping
- Added pypdf and duckduckgo-search dependencies

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-18 18:07:19 +02:00
Kaloyan Danchev
b3608b35fa Connect to Discord, switch to NVIDIA NIM providers 
- Enable Discord channel, respond to all messages from allowed users
- Switch all agents to NVIDIA NIM (Kimi K2.5, DeepSeek V3.1)
- Auto-approve all tools for non-interactive Docker deployment
- Fix tool call arguments serialization (dict → JSON string)
- Fix Dockerfile to copy source before uv sync

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-18 15:34:15 +02:00
Kaloyan Danchev
378d599125 Initial implementation of xtrm-agent multi-agent system 
Multi-agent AI automation system with shared message bus, specialized
roles (coder/researcher/reviewer), and deny-by-default security.

- Config system with Pydantic validation and YAML loading
- Async message bus with inter-agent delegation
- LLM providers: Anthropic (Claude) and LiteLLM (DeepSeek/Kimi/MiniMax)
- Tool system: registry, builtins (file/bash/web), approval engine, MCP client
- Agent engine with tool-calling loop and orchestrator for multi-agent management
- CLI channel (REPL) and Discord channel
- Docker + Dockge deployment config
- Typer CLI: chat, serve, status, agents commands

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-18 10:21:42 +02:00