Agentic Context Engine is an open-source engine that gives AI agents a persistent learning loop, helping them remember successful strategies and learn from failures across sessions. It is used to improve production agents, and also powers Kayba’s hosted service. Catalogue add-ons support workflows for operating and configuring the engine.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kayba-ai/agentic-context-engine --skill kayba-acegit clone --depth 1 https://github.com/kayba-ai/agentic-context-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-ace)<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-ace"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-ace/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-ace"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-ace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 114 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 117 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Rogue Agent · line 83 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Tool Misuse · line 114 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01154 |
| Opus 5.5 | $0.00000 | $0.00462 |
| Sonnet 5.5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
kayba-ace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACE — Learn from Traces
This skill ships learn_from_traces.py, a script that reads OpenClaw session
transcripts, feeds them through the ACE learning pipeline, and writes an
updated skillbook to disk.
Usage
python learn_from_traces.py [OPTIONS] [FILES...]
The script auto-discovers new sessions from ~/.openclaw/agents/<agent>/sessions/
and only processes files that haven't been processed before. Processed filenames
are tracked in ace_processed.txt.
Options
| Flag | Description |
|---|---|
--dry-run |
Parse sessions but skip the learning step (no LLM calls) |
--reprocess |
Ignore the processed log and reprocess all sessions |
--agent ID |
OpenClaw agent ID (default: $OPENCLAW_AGENT_ID or main) |
--output DIR |
Output directory for skillbook files (default: script directory) |
--opik |
Enable Opik observability logging |
Pass one or more JSONL file paths as positional arguments to process specific files instead of auto-discovering sessions.
Examples
Learn from all new sessions
python learn_from_traces.py
Discovers unprocessed sessions under ~/.openclaw/agents/main/sessions/,
runs the learning pipeline, and writes the updated skillbook.
Dry run (no LLM calls)
python learn_from_traces.py --dry-run
Parses and validates sessions without calling the LLM. Useful for checking that session files are readable before committing to a full run.
Process a specific trace file
python learn_from_traces.py ~/.openclaw/agents/main/sessions/f967d602.jsonl
Skips auto-discovery and processes only the given file. The processed log is not updated when files are passed directly.
Process multiple files
python learn_from_traces.py session1.jsonl session2.jsonl session3.jsonl
Reprocess all sessions
python learn_from_traces.py --reprocess
Ignores ace_processed.txt and reprocesses every session file. Useful after
upgrading ACE or when you want to rebuild the skillbook from scratch.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 160 lines · 0 tokens per session scan A 33810fe8c542
kayba-ace is a skill published in the GitHub repository kayba-ai/agentic-context-engine (2,604 stars, last pushed 28d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,154 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
titen-memory
Use the Titen MCP server to recall bounded evidence-grounded context, record verified durable signals, submit feedback, and coordinate checkpoints, leases, or handoffs. Use when work may benefit from prior project memory or when a verified outcome should be preserved for another agent; do not use it to capture raw…
dna-memory-loop
Use when a substantive task may depend on prior decisions, preferences, project state, workflows, errors, or open loops, or when a verified result should become reusable across Codex, Claude, Hermes, and an Obsidian vault.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
mem0-cli
Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0…