forcefield
An ultra-fast, lightweight, local-first AI agent harness for running specialized agents in Go
What XERJ indexed
Snapshot
The whole repository at commit fdff788f4e (2026-10-10). main is 26 commits ahead.
Selected work

“add opt-in isolated execution via Landlock”. 21 files, 1,088 lines in internal/sandbox, internal/config, cue.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-30. 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
aiai-agentsdeveloper-toolsgogolangharnessskills
Example questions
- How does forcefield implement ai?
- Where does forcefield handle “add opt-in isolated execution via Landlock”?
- What does internal/sandbox do in forcefield?
Inside the indexed corpus
- 596 files, 5.0 MB in total, about 8.6 KB per file.
- The selected commit changed 21 of those files (3.5%).
- Languages by size: Go 95.9%, PowerShell 1.8%, Shell 1.5%, CUE 0.5%, Makefile 0.2%.
- On GitHub since 2026-07-24, last push 2026-10-31, 228 commits on main.
- The pin is 26 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for fabledruns/forcefield on 2026-10-31, and the LICENSE file at commit fdff788f4e was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
FabledRuns (@fabledruns) has 1 selected repository on the hub.
Using XERJ with forcefield
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Ask questions about a GitHub repo without cloning it
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
The prompt
Paste it into your AI agent. It clones fabledruns/forcefield at the pinned commit and indexes it on your machine.
Search the GitHub repository fabledruns/forcefield with XERJ (https://hub.xerj.org/corpus/fabledruns--forcefield). 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/fabledruns/forcefield forcefield && git -C forcefield checkout fdff788f4ef1cdb11a359f2176257697f6cd0c42 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./forcefield --url http://127.0.0.1:9200 --prefix forcefield --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: Apache-2.0. Keep the copyright notice and credit the authors.
Related
FabledRunsAI, prompts and agents corporalibopenapicertstrapgnarkpardnchiu/Agenvoycyanxxy/transcription-agent-gocolibriproject-dev/colibri-sdk-go
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.