kazenai 0.1.0__tar.gz

kazenai-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

kazenai-0.1.0/PKG-INFO

@@ -0,0 +1,267 @@
+Metadata-Version: 2.4
+Name: kazenai
+Version: 0.1.0
+Summary: Reliability infrastructure for AI agents: Local-first budget & loop enforcement.
+Author-email: Dhavan Shah <founder@kazenai.com>
+License: Apache-2.0
+Project-URL: Homepage, https://kazenai.com
+Project-URL: Repository, https://github.com/kazenai-ai/kazenai-core
+Keywords: llm,agents,observability,finops,langchain
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: structlog>=24.1.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: pydantic-settings>=2.1.0
+Dynamic: license-file
+
+# kazenai-core
+
+> **Stop your AI agents from burning your budget. Catch loops before they catch you.**
+
+[![PyPI version](https://badge.fury.io/py/kazenai-finops.svg)](https://badge.fury.io/py/kazenai-finops)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Status: Building in Public](https://img.shields.io/badge/status-building%20in%20public-orange.svg)](https://x.com/kazenai)
+
+---
+
+## What is KazenAI?
+
+KazenAI is **reliability infrastructure for AI agents**.
+
+When you run an AI agent in production, three things will eventually go wrong:
+
+1. **It loops** — and burns your entire monthly LLM budget in 40 minutes
+2. **It fails silently** — returns 200 OK but the business outcome is wrong
+3. **You can't debug it** — because AI agents are non-deterministic and single-trace debugging is meaningless
+
+KazenAI intercepts every LLM and tool call your agent makes, enforces budget limits locally (no network required), detects loops before they become expensive, and gives you full observability — with one function call.
+
+```python
+from kazenai import monitor
+
+agent = monitor(
+    agent,
+    agent_id="support-agent",
+    api_key="kz_...",
+    max_budget_usd=5.00,
+    debug=True,           # see cost per call in your terminal
+)
+```
+
+That's it. Your agent code doesn't change.
+
+---
+
+## The problem in one screenshot
+
+```
+[KazenAI] step=1  gpt-4o-mini  cost=$0.0043  total=$0.0043  proj=$0.21/$5.00  OK
+[KazenAI] step=2  gpt-4o-mini  cost=$0.0041  total=$0.0084  proj=$0.19/$5.00  OK
+[KazenAI] step=8  gpt-4o-mini  cost=$0.0039  total=$0.43    proj=$4.91/$5.00  WARN:budget_87pct
+[KazenAI] step=9  gpt-4o-mini  BLOCKED:budget  spent=$5.00  limit=$5.00
+
+KazenBudgetExceeded: Run agent-001: budget $5.00 exceeded (spent $4.97, attempted $5.42)
+```
+
+No more waking up to a $47K bill.
+
+---
+
+## Features (MVP — shipping Week 1)
+
+- **`monitor(agent, ...)`** — wraps LangChain, AutoGen, and CrewAI agents with one call
+- **Local budget enforcement** — blocks calls before they're made, no network required, <1ms
+- **Real-time debug output** — `debug=True` prints cost + status after every LLM call
+- **Loop detection (H1)** — Jaccard similarity catches near-duplicate inputs before they spiral
+- **Loop detection (H2)** — tool chain fingerprinting catches recursive tool patterns
+- **Rate limiting** — `max_calls_per_minute` prevents runaway agents from moving too fast
+- **Event sampling** — `sample_rate=0.3` to control backend traffic at scale
+- **Offline resilience** — RetryQueue (SQLite) stores events locally if backend is down
+- **Parent-child tracing** — `RunContext` with `parent_step_id` for multi-agent pipelines
+- **Canonical event schema** — `KazenEvent` shared by SDK and backend (no field drift)
+- **OpenAI patcher** — transparent monkey-patch, no code changes required
+- **LangChain integration** — `KazenCallbackHandler` + `LangChainProxy`
+- **AutoGen integration** — wraps `initiate_chat`
+- **CrewAI integration** — wraps `kickoff()`
+
+## Planned Modules (Roadmap)
+
+- **AgentLens P1** — step-level trace capture dashboard (Month 2)
+- **AgentLens P2** — Probabilistic Replay Engine: run any trace N times, get statistical distribution of outcomes (Month 5) — *no competitor has built this*
+- **AgentLens P3** — Semantic Drift Monitor: detect when your agent's behaviour changes after a model update (Month 6)
+- **TypeScript SDK** — for Node.js agent frameworks (Month 6)
+
+---
+
+## Installation
+
+```bash
+pip install kazenai-finops
+```
+
+Python 3.10, 3.11, 3.12 supported. No C extensions. Installs in under 30 seconds.
+
+---
+
+## Quick Start
+
+### Raw OpenAI (no framework)
+
+```python
+import openai
+from kazenai import monitor, KazenBudgetExceeded
+
+client = openai.OpenAI()
+
+# monitor() patches the OpenAI client transparently
+with_monitoring = monitor(
+    client,
+    agent_id="my-agent",
+    api_key="kz_...",          # get yours at kazenai.com
+    max_budget_usd=0.50,
+    debug=True,
+)
+
+try:
+    for i in range(100):       # simulated loop
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[{"role": "user", "content": f"Step {i}: do the thing"}],
+        )
+except KazenBudgetExceeded as e:
+    print(f"Blocked at step {e.run_id}: spent ${e.spent:.4f}")
+```
+
+### LangChain
+
+```python
+from kazenai import monitor
+
+chain = your_langchain_chain  # LCEL chain, agent, etc.
+monitored = monitor(
+    chain,
+    agent_id="customer-support",
+    api_key="kz_...",
+    max_budget_usd=2.00,
+    debug=True,
+)
+
+result = monitored.invoke({"input": "help me with my order"})
+```
+
+### CrewAI
+
+```python
+from kazenai import monitor
+
+crew = YourCrew()
+monitored = monitor(
+    crew,
+    agent_id="research-crew",
+    api_key="kz_...",
+    max_budget_usd=10.00,
+    h2_max_reps=3,   # block if same tool chain repeats 3 times
+)
+
+result = monitored.kickoff(inputs={"topic": "AI trends"})
+```
+
+---
+
+## Why local enforcement matters
+
+Most observability tools record what happened. **KazenAI blocks what's about to happen.**
+
+```
+Traditional tools:  LLM call → response → log cost → dashboard shows $47K
+KazenAI:            Pre-flight check → BLOCKED → LLM call never made
+```
+
+Local enforcement means:
+- **No network dependency** — works with `backend_url=None`
+- **No latency added** — budget check completes in <1ms
+- **No backend outage = no protection failure** — the agent doesn't need to reach our servers to be protected
+
+---
+
+## Repository Structure
+
+```
+kazenai-core/
+├── kazenai/
+│   ├── __init__.py          # public API: monitor()
+│   ├── schema.py            # canonical KazenEvent (shared SDK + backend)
+│   ├── context.py           # RunContext with parent_step_id
+│   ├── monitor.py           # monitor() entry point
+│   ├── interceptor.py       # LLM/tool call interception
+│   ├── enforcement.py       # local budget + rate limit enforcement
+│   ├── loop_detector.py     # H1 (Jaccard) + H2 (chain fingerprint)
+│   ├── cost_tracker.py      # 14-model pricing table
+│   ├── client.py            # async API client + sampling
+│   ├── retry_queue.py       # SQLite retry queue for offline resilience
+│   ├── debug.py             # debug=True terminal output
+│   ├── config.py            # pydantic-settings
+│   └── integrations/
+│       ├── langchain.py
+│       ├── autogen.py
+│       ├── crewai.py
+│       └── generic.py
+├── examples/
+│   ├── basic_agent.py       # raw OpenAI example
+│   ├── langchain_example.py
+│   ├── loop_example.py      # trigger loop detection
+│   └── benchmark_latency.py # verify <5ms overhead
+├── tests/
+├── pyproject.toml
+└── README.md
+```
+
+---
+
+## Design principles
+
+1. **Local-first enforcement** — SDK must block without backend
+2. **Zero-blocking** — SDK overhead <5ms on hot path
+3. **Fail-open always** — internal errors never crash your agent
+4. **Canonical schema** — KazenEvent used by both SDK and backend (`extra='forbid'`)
+5. **DX over features** — `debug=True` gives value in 2 minutes
+
+---
+
+## Star this repo ⭐
+
+If you've ever woken up to an unexpected LLM bill, or spent hours debugging an agent that returned 200 OK but did nothing useful — **star this repo**. It tells us this matters to you, and it helps us ship faster.
+
+We're building in public. Follow [@kazenai](https://x.com/kazenai) for weekly progress updates.
+
+---
+
+## Status
+
+**Week 1** — Building core SDK  
+**Week 2** — Design partner onboarding  
+**Week 3** — Hosted dashboard + paid tiers  
+**Week 4** — Public launch
+
+Early access: [kazenai.com](https://kazenai.com) or email **founder@kazenai.com**
+
+---
+
+## Contributing
+
+We're pre-1.0 and moving fast. The best way to contribute right now is:
+
+1. ⭐ Star the repo
+2. Open an issue describing a pain point you've hit with AI agent costs or loops
+3. Try the examples and report what breaks
+
+Full contribution guide coming with v1.0.
+
+---
+
+## License
+
+Apache 2.0 — use it for anything, attribution appreciated.

kazenai-0.1.0/README.md

@@ -0,0 +1,249 @@
+# kazenai-core
+
+> **Stop your AI agents from burning your budget. Catch loops before they catch you.**
+
+[![PyPI version](https://badge.fury.io/py/kazenai-finops.svg)](https://badge.fury.io/py/kazenai-finops)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Status: Building in Public](https://img.shields.io/badge/status-building%20in%20public-orange.svg)](https://x.com/kazenai)
+
+---
+
+## What is KazenAI?
+
+KazenAI is **reliability infrastructure for AI agents**.
+
+When you run an AI agent in production, three things will eventually go wrong:
+
+1. **It loops** — and burns your entire monthly LLM budget in 40 minutes
+2. **It fails silently** — returns 200 OK but the business outcome is wrong
+3. **You can't debug it** — because AI agents are non-deterministic and single-trace debugging is meaningless
+
+KazenAI intercepts every LLM and tool call your agent makes, enforces budget limits locally (no network required), detects loops before they become expensive, and gives you full observability — with one function call.
+
+```python
+from kazenai import monitor
+
+agent = monitor(
+    agent,
+    agent_id="support-agent",
+    api_key="kz_...",
+    max_budget_usd=5.00,
+    debug=True,           # see cost per call in your terminal
+)
+```
+
+That's it. Your agent code doesn't change.
+
+---
+
+## The problem in one screenshot
+
+```
+[KazenAI] step=1  gpt-4o-mini  cost=$0.0043  total=$0.0043  proj=$0.21/$5.00  OK
+[KazenAI] step=2  gpt-4o-mini  cost=$0.0041  total=$0.0084  proj=$0.19/$5.00  OK
+[KazenAI] step=8  gpt-4o-mini  cost=$0.0039  total=$0.43    proj=$4.91/$5.00  WARN:budget_87pct
+[KazenAI] step=9  gpt-4o-mini  BLOCKED:budget  spent=$5.00  limit=$5.00
+
+KazenBudgetExceeded: Run agent-001: budget $5.00 exceeded (spent $4.97, attempted $5.42)
+```
+
+No more waking up to a $47K bill.
+
+---
+
+## Features (MVP — shipping Week 1)
+
+- **`monitor(agent, ...)`** — wraps LangChain, AutoGen, and CrewAI agents with one call
+- **Local budget enforcement** — blocks calls before they're made, no network required, <1ms
+- **Real-time debug output** — `debug=True` prints cost + status after every LLM call
+- **Loop detection (H1)** — Jaccard similarity catches near-duplicate inputs before they spiral
+- **Loop detection (H2)** — tool chain fingerprinting catches recursive tool patterns
+- **Rate limiting** — `max_calls_per_minute` prevents runaway agents from moving too fast
+- **Event sampling** — `sample_rate=0.3` to control backend traffic at scale
+- **Offline resilience** — RetryQueue (SQLite) stores events locally if backend is down
+- **Parent-child tracing** — `RunContext` with `parent_step_id` for multi-agent pipelines
+- **Canonical event schema** — `KazenEvent` shared by SDK and backend (no field drift)
+- **OpenAI patcher** — transparent monkey-patch, no code changes required
+- **LangChain integration** — `KazenCallbackHandler` + `LangChainProxy`
+- **AutoGen integration** — wraps `initiate_chat`
+- **CrewAI integration** — wraps `kickoff()`
+
+## Planned Modules (Roadmap)
+
+- **AgentLens P1** — step-level trace capture dashboard (Month 2)
+- **AgentLens P2** — Probabilistic Replay Engine: run any trace N times, get statistical distribution of outcomes (Month 5) — *no competitor has built this*
+- **AgentLens P3** — Semantic Drift Monitor: detect when your agent's behaviour changes after a model update (Month 6)
+- **TypeScript SDK** — for Node.js agent frameworks (Month 6)
+
+---
+
+## Installation
+
+```bash
+pip install kazenai-finops
+```
+
+Python 3.10, 3.11, 3.12 supported. No C extensions. Installs in under 30 seconds.
+
+---
+
+## Quick Start
+
+### Raw OpenAI (no framework)
+
+```python
+import openai
+from kazenai import monitor, KazenBudgetExceeded
+
+client = openai.OpenAI()
+
+# monitor() patches the OpenAI client transparently
+with_monitoring = monitor(
+    client,
+    agent_id="my-agent",
+    api_key="kz_...",          # get yours at kazenai.com
+    max_budget_usd=0.50,
+    debug=True,
+)
+
+try:
+    for i in range(100):       # simulated loop
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[{"role": "user", "content": f"Step {i}: do the thing"}],
+        )
+except KazenBudgetExceeded as e:
+    print(f"Blocked at step {e.run_id}: spent ${e.spent:.4f}")
+```
+
+### LangChain
+
+```python
+from kazenai import monitor
+
+chain = your_langchain_chain  # LCEL chain, agent, etc.
+monitored = monitor(
+    chain,
+    agent_id="customer-support",
+    api_key="kz_...",
+    max_budget_usd=2.00,
+    debug=True,
+)
+
+result = monitored.invoke({"input": "help me with my order"})
+```
+
+### CrewAI
+
+```python
+from kazenai import monitor
+
+crew = YourCrew()
+monitored = monitor(
+    crew,
+    agent_id="research-crew",
+    api_key="kz_...",
+    max_budget_usd=10.00,
+    h2_max_reps=3,   # block if same tool chain repeats 3 times
+)
+
+result = monitored.kickoff(inputs={"topic": "AI trends"})
+```
+
+---
+
+## Why local enforcement matters
+
+Most observability tools record what happened. **KazenAI blocks what's about to happen.**
+
+```
+Traditional tools:  LLM call → response → log cost → dashboard shows $47K
+KazenAI:            Pre-flight check → BLOCKED → LLM call never made
+```
+
+Local enforcement means:
+- **No network dependency** — works with `backend_url=None`
+- **No latency added** — budget check completes in <1ms
+- **No backend outage = no protection failure** — the agent doesn't need to reach our servers to be protected
+
+---
+
+## Repository Structure
+
+```
+kazenai-core/
+├── kazenai/
+│   ├── __init__.py          # public API: monitor()
+│   ├── schema.py            # canonical KazenEvent (shared SDK + backend)
+│   ├── context.py           # RunContext with parent_step_id
+│   ├── monitor.py           # monitor() entry point
+│   ├── interceptor.py       # LLM/tool call interception
+│   ├── enforcement.py       # local budget + rate limit enforcement
+│   ├── loop_detector.py     # H1 (Jaccard) + H2 (chain fingerprint)
+│   ├── cost_tracker.py      # 14-model pricing table
+│   ├── client.py            # async API client + sampling
+│   ├── retry_queue.py       # SQLite retry queue for offline resilience
+│   ├── debug.py             # debug=True terminal output
+│   ├── config.py            # pydantic-settings
+│   └── integrations/
+│       ├── langchain.py
+│       ├── autogen.py
+│       ├── crewai.py
+│       └── generic.py
+├── examples/
+│   ├── basic_agent.py       # raw OpenAI example
+│   ├── langchain_example.py
+│   ├── loop_example.py      # trigger loop detection
+│   └── benchmark_latency.py # verify <5ms overhead
+├── tests/
+├── pyproject.toml
+└── README.md
+```
+
+---
+
+## Design principles
+
+1. **Local-first enforcement** — SDK must block without backend
+2. **Zero-blocking** — SDK overhead <5ms on hot path
+3. **Fail-open always** — internal errors never crash your agent
+4. **Canonical schema** — KazenEvent used by both SDK and backend (`extra='forbid'`)
+5. **DX over features** — `debug=True` gives value in 2 minutes
+
+---
+
+## Star this repo ⭐
+
+If you've ever woken up to an unexpected LLM bill, or spent hours debugging an agent that returned 200 OK but did nothing useful — **star this repo**. It tells us this matters to you, and it helps us ship faster.
+
+We're building in public. Follow [@kazenai](https://x.com/kazenai) for weekly progress updates.
+
+---
+
+## Status
+
+**Week 1** — Building core SDK  
+**Week 2** — Design partner onboarding  
+**Week 3** — Hosted dashboard + paid tiers  
+**Week 4** — Public launch
+
+Early access: [kazenai.com](https://kazenai.com) or email **founder@kazenai.com**
+
+---
+
+## Contributing
+
+We're pre-1.0 and moving fast. The best way to contribute right now is:
+
+1. ⭐ Star the repo
+2. Open an issue describing a pain point you've hit with AI agent costs or loops
+3. Try the examples and report what breaks
+
+Full contribution guide coming with v1.0.
+
+---
+
+## License
+
+Apache 2.0 — use it for anything, attribution appreciated.

kazenai-0.1.0/kazenai.egg-info/PKG-INFO

@@ -0,0 +1,267 @@
+Metadata-Version: 2.4
+Name: kazenai
+Version: 0.1.0
+Summary: Reliability infrastructure for AI agents: Local-first budget & loop enforcement.
+Author-email: Dhavan Shah <founder@kazenai.com>
+License: Apache-2.0
+Project-URL: Homepage, https://kazenai.com
+Project-URL: Repository, https://github.com/kazenai-ai/kazenai-core
+Keywords: llm,agents,observability,finops,langchain
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: structlog>=24.1.0
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: pydantic-settings>=2.1.0
+Dynamic: license-file
+
+# kazenai-core
+
+> **Stop your AI agents from burning your budget. Catch loops before they catch you.**
+
+[![PyPI version](https://badge.fury.io/py/kazenai-finops.svg)](https://badge.fury.io/py/kazenai-finops)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+[![Status: Building in Public](https://img.shields.io/badge/status-building%20in%20public-orange.svg)](https://x.com/kazenai)
+
+---
+
+## What is KazenAI?
+
+KazenAI is **reliability infrastructure for AI agents**.
+
+When you run an AI agent in production, three things will eventually go wrong:
+
+1. **It loops** — and burns your entire monthly LLM budget in 40 minutes
+2. **It fails silently** — returns 200 OK but the business outcome is wrong
+3. **You can't debug it** — because AI agents are non-deterministic and single-trace debugging is meaningless
+
+KazenAI intercepts every LLM and tool call your agent makes, enforces budget limits locally (no network required), detects loops before they become expensive, and gives you full observability — with one function call.
+
+```python
+from kazenai import monitor
+
+agent = monitor(
+    agent,
+    agent_id="support-agent",
+    api_key="kz_...",
+    max_budget_usd=5.00,
+    debug=True,           # see cost per call in your terminal
+)
+```
+
+That's it. Your agent code doesn't change.
+
+---
+
+## The problem in one screenshot
+
+```
+[KazenAI] step=1  gpt-4o-mini  cost=$0.0043  total=$0.0043  proj=$0.21/$5.00  OK
+[KazenAI] step=2  gpt-4o-mini  cost=$0.0041  total=$0.0084  proj=$0.19/$5.00  OK
+[KazenAI] step=8  gpt-4o-mini  cost=$0.0039  total=$0.43    proj=$4.91/$5.00  WARN:budget_87pct
+[KazenAI] step=9  gpt-4o-mini  BLOCKED:budget  spent=$5.00  limit=$5.00
+
+KazenBudgetExceeded: Run agent-001: budget $5.00 exceeded (spent $4.97, attempted $5.42)
+```
+
+No more waking up to a $47K bill.
+
+---
+
+## Features (MVP — shipping Week 1)
+
+- **`monitor(agent, ...)`** — wraps LangChain, AutoGen, and CrewAI agents with one call
+- **Local budget enforcement** — blocks calls before they're made, no network required, <1ms
+- **Real-time debug output** — `debug=True` prints cost + status after every LLM call
+- **Loop detection (H1)** — Jaccard similarity catches near-duplicate inputs before they spiral
+- **Loop detection (H2)** — tool chain fingerprinting catches recursive tool patterns
+- **Rate limiting** — `max_calls_per_minute` prevents runaway agents from moving too fast
+- **Event sampling** — `sample_rate=0.3` to control backend traffic at scale
+- **Offline resilience** — RetryQueue (SQLite) stores events locally if backend is down
+- **Parent-child tracing** — `RunContext` with `parent_step_id` for multi-agent pipelines
+- **Canonical event schema** — `KazenEvent` shared by SDK and backend (no field drift)
+- **OpenAI patcher** — transparent monkey-patch, no code changes required
+- **LangChain integration** — `KazenCallbackHandler` + `LangChainProxy`
+- **AutoGen integration** — wraps `initiate_chat`
+- **CrewAI integration** — wraps `kickoff()`
+
+## Planned Modules (Roadmap)
+
+- **AgentLens P1** — step-level trace capture dashboard (Month 2)
+- **AgentLens P2** — Probabilistic Replay Engine: run any trace N times, get statistical distribution of outcomes (Month 5) — *no competitor has built this*
+- **AgentLens P3** — Semantic Drift Monitor: detect when your agent's behaviour changes after a model update (Month 6)
+- **TypeScript SDK** — for Node.js agent frameworks (Month 6)
+
+---
+
+## Installation
+
+```bash
+pip install kazenai-finops
+```
+
+Python 3.10, 3.11, 3.12 supported. No C extensions. Installs in under 30 seconds.
+
+---
+
+## Quick Start
+
+### Raw OpenAI (no framework)
+
+```python
+import openai
+from kazenai import monitor, KazenBudgetExceeded
+
+client = openai.OpenAI()
+
+# monitor() patches the OpenAI client transparently
+with_monitoring = monitor(
+    client,
+    agent_id="my-agent",
+    api_key="kz_...",          # get yours at kazenai.com
+    max_budget_usd=0.50,
+    debug=True,
+)
+
+try:
+    for i in range(100):       # simulated loop
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[{"role": "user", "content": f"Step {i}: do the thing"}],
+        )
+except KazenBudgetExceeded as e:
+    print(f"Blocked at step {e.run_id}: spent ${e.spent:.4f}")
+```
+
+### LangChain
+
+```python
+from kazenai import monitor
+
+chain = your_langchain_chain  # LCEL chain, agent, etc.
+monitored = monitor(
+    chain,
+    agent_id="customer-support",
+    api_key="kz_...",
+    max_budget_usd=2.00,
+    debug=True,
+)
+
+result = monitored.invoke({"input": "help me with my order"})
+```
+
+### CrewAI
+
+```python
+from kazenai import monitor
+
+crew = YourCrew()
+monitored = monitor(
+    crew,
+    agent_id="research-crew",
+    api_key="kz_...",
+    max_budget_usd=10.00,
+    h2_max_reps=3,   # block if same tool chain repeats 3 times
+)
+
+result = monitored.kickoff(inputs={"topic": "AI trends"})
+```
+
+---
+
+## Why local enforcement matters
+
+Most observability tools record what happened. **KazenAI blocks what's about to happen.**
+
+```
+Traditional tools:  LLM call → response → log cost → dashboard shows $47K
+KazenAI:            Pre-flight check → BLOCKED → LLM call never made
+```
+
+Local enforcement means:
+- **No network dependency** — works with `backend_url=None`
+- **No latency added** — budget check completes in <1ms
+- **No backend outage = no protection failure** — the agent doesn't need to reach our servers to be protected
+
+---
+
+## Repository Structure
+
+```
+kazenai-core/
+├── kazenai/
+│   ├── __init__.py          # public API: monitor()
+│   ├── schema.py            # canonical KazenEvent (shared SDK + backend)
+│   ├── context.py           # RunContext with parent_step_id
+│   ├── monitor.py           # monitor() entry point
+│   ├── interceptor.py       # LLM/tool call interception
+│   ├── enforcement.py       # local budget + rate limit enforcement
+│   ├── loop_detector.py     # H1 (Jaccard) + H2 (chain fingerprint)
+│   ├── cost_tracker.py      # 14-model pricing table
+│   ├── client.py            # async API client + sampling
+│   ├── retry_queue.py       # SQLite retry queue for offline resilience
+│   ├── debug.py             # debug=True terminal output
+│   ├── config.py            # pydantic-settings
+│   └── integrations/
+│       ├── langchain.py
+│       ├── autogen.py
+│       ├── crewai.py
+│       └── generic.py
+├── examples/
+│   ├── basic_agent.py       # raw OpenAI example
+│   ├── langchain_example.py
+│   ├── loop_example.py      # trigger loop detection
+│   └── benchmark_latency.py # verify <5ms overhead
+├── tests/
+├── pyproject.toml
+└── README.md
+```
+
+---
+
+## Design principles
+
+1. **Local-first enforcement** — SDK must block without backend
+2. **Zero-blocking** — SDK overhead <5ms on hot path
+3. **Fail-open always** — internal errors never crash your agent
+4. **Canonical schema** — KazenEvent used by both SDK and backend (`extra='forbid'`)
+5. **DX over features** — `debug=True` gives value in 2 minutes
+
+---
+
+## Star this repo ⭐
+
+If you've ever woken up to an unexpected LLM bill, or spent hours debugging an agent that returned 200 OK but did nothing useful — **star this repo**. It tells us this matters to you, and it helps us ship faster.
+
+We're building in public. Follow [@kazenai](https://x.com/kazenai) for weekly progress updates.
+
+---
+
+## Status
+
+**Week 1** — Building core SDK  
+**Week 2** — Design partner onboarding  
+**Week 3** — Hosted dashboard + paid tiers  
+**Week 4** — Public launch
+
+Early access: [kazenai.com](https://kazenai.com) or email **founder@kazenai.com**
+
+---
+
+## Contributing
+
+We're pre-1.0 and moving fast. The best way to contribute right now is:
+
+1. ⭐ Star the repo
+2. Open an issue describing a pain point you've hit with AI agent costs or loops
+3. Try the examples and report what breaks
+
+Full contribution guide coming with v1.0.
+
+---
+
+## License
+
+Apache 2.0 — use it for anything, attribution appreciated.

kazenai-0.1.0/kazenai.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+./kazenai/__init__.py
+kazenai/__init__.py
+kazenai.egg-info/PKG-INFO
+kazenai.egg-info/SOURCES.txt
+kazenai.egg-info/dependency_links.txt
+kazenai.egg-info/requires.txt
+kazenai.egg-info/top_level.txt

kazenai-0.1.0/kazenai.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

kazenai-0.1.0/kazenai.egg-info/requires.txt

@@ -0,0 +1,4 @@
+pydantic>=2.6.0
+structlog>=24.1.0
+aiohttp>=3.9.0
+pydantic-settings>=2.1.0

kazenai-0.1.0/kazenai.egg-info/top_level.txt

@@ -0,0 +1 @@
+kazenai

kazenai-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "kazenai"  # Matches your README installation instructions
+version = "0.1.0"
+description = "Reliability infrastructure for AI agents: Local-first budget & loop enforcement."
+readme = "README.md"
+requires-python = ">=3.10" # v4 TDD specifies 3.10+ for modern Typing/ContextVars
+license = { text = "Apache-2.0" } # Explicitly state the license type here
+authors = [{ name = "Dhavan Shah", email = "founder@kazenai.com" }]
+keywords = ["llm", "agents", "observability", "finops", "langchain"]
+
+dependencies = [
+  "pydantic>=2.6.0",
+  "structlog>=24.1.0",
+  "aiohttp>=3.9.0",
+  "pydantic-settings>=2.1.0", # Added: Necessary for your config.py logic
+]
+
+[project.urls]
+"Homepage" = "https://kazenai.com"
+"Repository" = "https://github.com/kazenai-ai/kazenai-core"
+
+[tool.setuptools]
+# Ensure it only picks up the 'kazenai' folder, not 'tests' or 'examples'
+packages = ["kazenai"]
+package-dir = {"" = "."}

kazenai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+