PrimeIntellect-ai

Message an agent's parent, siblings, or direct children through the daemon. Use the family roster to discover reachable agents and send direct text without spoofing sender identity.

Read-only observation of an agent's parent, siblings, and direct children. Use to inspect family status and bounded recent-message previews without mutating sessions.

Load an on-disk image (PNG, JPEG, GIF, WebP) into the model's context as a viewable attachment so the model can directly SEE it — for screenshots, diagrams, charts, photos, or scanned pages. Use this when you need to perceive an image's visual contents.…

Check context usage and compact the conversation from the Python REPL. Use when context is filling up and substantial work remains, so the session is summarized and you keep working instead of stopping early.

Replace an exact, unique string in an existing file. Use for targeted single-occurrence edits to files from the Python kernel instead of rewriting the whole file.

Manage the persistent thread goal from the Python REPL. Use to read goal status and budget usage, to start a goal when the user explicitly asks for one, or to mark the active goal complete once its objective is fully achieved.

Read and write Linear issues, projects, cycles, comments, and more via Linear's official MCP server. Tools are auto-discovered from the server at runtime.

Search Notion and read/create/update pages and databases via Notion's official hosted MCP server. Tools are auto-discovered from the server at runtime.

Find, start, use, and stop the local run dashboard for metrics, configs, traces, logs, and reports. Use when asked for its URL, to watch or inspect a run, to control the open dashboard, or to create a cited dashboard report explicitly requested by the user.

Monitor an ongoing prime-rl training run — find the output directory, tail logs, check key metrics, inspect SLURM jobs, and restart safely. Use when asked to check on a run, debug training, or investigate performance.

Launch and monitor prime-rl training runs. Use when starting, supervising, or debugging an RL/SFT run. Routes to `start-run` (entrypoints + how to launch) and `monitor-run` (logs, metrics, check-ins).

How the prime-rl config system works — TOML files, CLI overrides, composition, and special patterns. Use when creating configs, debugging config errors, or overriding values via CLI.

How to launch prime-rl training runs — the `rl`, `sft`, `inference`, and `evals` entrypoints, their config classes, and single-node/SLURM/dry-run modes. Use when starting a run or picking the right entrypoint.

How to install prime-rl and its optional dependencies. Use when setting up the project, installing extras like DeepEP for multi-node expert parallelism, or troubleshooting dependency issues.

How prime-rl vendors, builds, and ships CUDA kernels (the `deps/prime-kernels` submodule and the `prime-kernels` wheel). Use when adding a kernel, building it locally, calling one from training code, or publishing prebuilt wheels.

How to prepare and publish GitHub releases for prime-rl. Use when drafting release notes, tagging versions, or publishing releases.

Release a stable verifiers version from main to PyPI and GitHub.

Run and evaluate verifiers tasksets. Set up the necessary config files and observe the runs and their results.

Create or migrate native verifiers.v1 taskset, environment, and harness packages. Use to build a taskset, port a benchmark, add task tools, script or model a user, build a multi-agent environment, package an agent harness, or migrate an existing v0…

Run interactive brainstorming across verifiers tasksets, evaluations, GEPA, and RL training. Use when the user wants ideation, literature scanning, concept teaching, roadmap planning, or research program design grounded in local CLI sources, verifiers, and RL…

Install and run a verifiers environment — smoke testing during development and full benchmark evals. Covers the `eval` CLI for the tasksets. Use while developing/iterating on an environment, when running/evaluating/benchmarking one, or when the user mentions…