agent-bridge-suite
Cross-IDE Episodic Memory and Multi-Model Speculative Consensus Suite bridging Antigravity and Claude Code
What XERJ indexed
Snapshot
The whole repository at commit ad0ef145ec. It is the newest commit on main.
Selected work

Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
adversarial-reviewai-agentsantigravitybm25claude-codecode-qualitydeveloper-toolsepisodic-memory
Example questions
- How does agent-bridge-suite implement adversarial-review?
- Show the ai-agents code in agent-bridge-suite.
Inside the indexed corpus
- 52 files, 238.6 KB in total, about 4.6 KB per file.
- Languages by size: TypeScript 81.4%, JavaScript 18.6%.
- On GitHub since 2026-10-27, last push 2026-10-27, 26 commits on main.
Licence on GitHub and in the corpus
GitHub reported MIT for roedyrustam/agent-bridge-suite on 2026-10-31, and the LICENSE file at commit ad0ef145ec was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Roedy Rustam (@roedyrustam) has 6 selected repositories on the hub.
Their other repository pages: roedyrustam/vibes-plug, roedyrustam/sinapsai, roedyrustam/cinematic-motion-engine, roedyrustam/dev-flow-timer, roedyrustam/opentalon.
Using XERJ with agent-bridge-suite
- Code search MCP for Claude Code: cite file:line, not grep agent-bridge-suite is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor agent-bridge-suite is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones roedyrustam/agent-bridge-suite at the pinned commit and indexes it on your machine.
Search the GitHub repository roedyrustam/agent-bridge-suite with XERJ (https://hub.xerj.org/corpus/roedyrustam--agent-bridge-suite). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/roedyrustam/agent-bridge-suite agent-bridge-suite && git -C agent-bridge-suite checkout ad0ef145ec9d872aec976f7bda8f3956055d26a3 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./agent-bridge-suite --url http://127.0.0.1:9200 --prefix agent-bridge-suite --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Roedy RustamAI, prompts and agents corporaautogendunorth595--xrpl-did-mcpcameltailucanh/offload-mcp-serverGabrielMartinMoran/mindrigour-labs/rigour
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.