agentic-context-engine vs reef
Learning loop for any agent: reflect on failures, distill strategies into a Skillbook, inject them next run — 2x consistency on Tau2, 49% token cuts. LiteLLM-based, 100+ providers. — versus — Continual-learning infra for self-improving agents: serve traffic (OpenAI/Anthropic-compatible), match feedback to runs, train weights via Slime/SGLang or evolve the harness, ship versioned updates.
Overlaps on the harness-optimisation path: both distil feedback into improved prompts/skills for the next run; ACE is a lightweight library, Reef adds serving, evaluation gates and version history.
| agentic-context-engine | reef | |
|---|---|---|
| Stars | 2.6k | 911 |
| Forks | 309 | 57 |
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 13 days ago | yesterday |
| Topics | memory, agents | training, agents |
| Curated connections | 7 | 5 |
agentic-context-engine — the curator's take
The in-process answer to 'my agent repeats the same mistakes': wrap your agent, feed it corrections, and ACE extracts reusable strategies it injects on later runs — no fine-tuning, no reward signals, and the numbers are concrete (2x pass^4 on Tau2, ~$1.50 to learn its way through a 14k-line translation). Pick it over a memory *service* when you want the learning inside your Python process rather than behind an HTTP API. NOT magic memory: strategies come from explicit feedback loops you wire up, quality follows the judge model, and the open-source engine is the on-ramp to the hosted Kayba product — check where the managed line lands before betting infra on it.
reef — the curator's take
Reef is the missing layer between an inference engine and an RL trainer: it serves live requests, ties feedback back to recorded interactions, runs a recipe (weight training via Slime, or prompt/rule/skill optimisation with no GPUs), evaluates candidates, and commits accepted versions with git-lfs history — all while staying online. Use it when you have a real feedback signal and want the agent to keep improving in production rather than in a one-off training run. Not for you if you just need a gateway or an eval harness, or if your model is a closed API and you have no harness surface to evolve. Weight-training path needs a supported GPU stack; harness-only path runs against any endpoint.