Dušan Jolović jolovicdev

🎯

Focusing

12 followers · 4 following

Block or report jolovicdev

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Add an optional note

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Overview Repositories 16 Projects Packages Stars 4

Overview
Repositories
Projects
Packages
Stars

jolovicdev/README.md

Most agent code is a prompt in a while-loop. I'm interested in the part underneath: what happens when the run dies halfway, when the context outlives the session, when a tool call has to be able to be wrong safely.

flowchart TB
    subgraph runtime [" Runtime "]
        BG["blackgeorge<br/><i>tool-calling, orchestration</i>"]
    end
    subgraph agents [" Agents "]
        DSR["ds-review<br/><i>PR review</i>"]
        SH["shandu<br/><i>deep research</i>"]
        SRC["sourcery<br/><i>extraction</i>"]
    end
    subgraph memory [" Memory "]
        AD["anchor-db<br/><i>code-local context over MCP</i>"]
    end
    subgraph infra [" Infrastructure "]
        CW["crawlwall"]
        HW["holloway"]
        CSH["cashet"]
    end
    BG --> DSR

Agents

blackgeorge Python
Agent framework for LLM tool-calling and multi-agent orchestration. The layer ds-review runs on.

ds-review Python
Multi-agent PR reviewer. Starts from the diff, pulls the related code context, and comments only on findings tied to changed lines. Runs on DeepSeek for the 1M-token window, which is what makes whole-repo context practical rather than theoretical.

shandu Python
Deep research agent. Multi-agent search and scraping with source-credibility scoring, producing citation-backed reports. Model-agnostic through LiteLLM.

sourcery Python
Structured extraction from documents. Define a Pydantic schema, get typed entities back with exact source spans. PDFs, HTML, long text, OCR.

Memory

anchor-db Go
Durable code-local memory for agents. Context lives in the Git repo beside the code it describes, served over MCP, CLI, HTTP, and a browser UI, so the reasoning behind a decision survives the session that produced it.

Infrastructure

crawlwall Go
Caddy module for AI crawler access control. Bot verification, rate limiting, shadow-mode rollout, SQLite ledgers, signed crawl receipts.

holloway Go
Self-hosted webhook relay. Every webhook persists to SQLite before delivery, so nothing is lost when the client is offline. Live dashboard, one-click replay.

cashet Python
Content-addressable memoization cache. Redis-backed, async, inspectable from the CLI.

Pinned Loading

shandu shandu Public

Open-source deep research agent: multi-agent web search, scraping, source-credibility scoring, and citation-backed reports with any LiteLLM model

Python 9
hayduk hayduk Public

Graphical attack management console for Metasploit: the lineage of Armitage as a single Go binary with a browser UI. Live network topology, campaign workflows, Hail Mary, sessions, report export, a…

TypeScript 1
ds-review ds-review Public

Self-hosted AI code reviewer for GitHub pull requests. DeepSeek-V4 + Blackgeorge multi-agent pipeline posts diff-anchored findings with severity badges and suggestions. Runs as a GitHub Action or y…

Python 2
blackgeorge blackgeorge Public

Python Agent Framework for LLM Tool-Calling and Multi-Agent Orchestration

Python
sourcery sourcery Public

Extract structured data from documents with LLMs. Define schemas in Pydantic and get typed entities with exact source spans. Handles PDFs, HTML, long text, and OCR.

Python 4
anchor-db anchor-db Public

MCP server that gives AI coding agents persistent memory of your codebase: notes pinned to files, spans, and symbols that survive refactors. Works with Claude Code, Cursor, and any MCP host.

Go