agentegrity 0.2.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. agentegrity-0.2.0/.gitignore +36 -0
  2. agentegrity-0.2.0/LICENSE +189 -0
  3. agentegrity-0.2.0/MANIFESTO.md +132 -0
  4. agentegrity-0.2.0/PKG-INFO +328 -0
  5. agentegrity-0.2.0/README.md +286 -0
  6. agentegrity-0.2.0/agentegrity-glossary.md +154 -0
  7. agentegrity-0.2.0/examples/basic_evaluation.py +112 -0
  8. agentegrity-0.2.0/examples/claude_adapter.py +68 -0
  9. agentegrity-0.2.0/examples/custom_validator.py +127 -0
  10. agentegrity-0.2.0/examples/runtime_monitoring.py +126 -0
  11. agentegrity-0.2.0/pyproject.toml +90 -0
  12. agentegrity-0.2.0/spec/SPECIFICATION.md +404 -0
  13. agentegrity-0.2.0/spec/layers/adversarial-layer.md +101 -0
  14. agentegrity-0.2.0/spec/layers/cortical-layer.md +114 -0
  15. agentegrity-0.2.0/spec/layers/governance-layer.md +149 -0
  16. agentegrity-0.2.0/spec/properties/adversarial-coherence.md +108 -0
  17. agentegrity-0.2.0/spec/properties/environmental-portability.md +88 -0
  18. agentegrity-0.2.0/spec/properties/verifiable-assurance.md +109 -0
  19. agentegrity-0.2.0/src/agentegrity/__init__.py +27 -0
  20. agentegrity-0.2.0/src/agentegrity/adapters/__init__.py +10 -0
  21. agentegrity-0.2.0/src/agentegrity/adapters/base.py +96 -0
  22. agentegrity-0.2.0/src/agentegrity/adapters/claude.py +460 -0
  23. agentegrity-0.2.0/src/agentegrity/core/__init__.py +16 -0
  24. agentegrity-0.2.0/src/agentegrity/core/attestation.py +244 -0
  25. agentegrity-0.2.0/src/agentegrity/core/evaluator.py +418 -0
  26. agentegrity-0.2.0/src/agentegrity/core/monitor.py +251 -0
  27. agentegrity-0.2.0/src/agentegrity/core/profile.py +196 -0
  28. agentegrity-0.2.0/src/agentegrity/layers/__init__.py +5 -0
  29. agentegrity-0.2.0/src/agentegrity/layers/adversarial.py +305 -0
  30. agentegrity-0.2.0/src/agentegrity/layers/cortical.py +440 -0
  31. agentegrity-0.2.0/src/agentegrity/layers/cortical_llm.py +304 -0
  32. agentegrity-0.2.0/src/agentegrity/layers/governance.py +392 -0
  33. agentegrity-0.2.0/src/agentegrity/layers/recovery.py +272 -0
  34. agentegrity-0.2.0/src/agentegrity/sdk/__init__.py +3 -0
  35. agentegrity-0.2.0/src/agentegrity/sdk/client.py +237 -0
  36. agentegrity-0.2.0/tests/__init__.py +0 -0
  37. agentegrity-0.2.0/tests/test_adapter_claude.py +184 -0
  38. agentegrity-0.2.0/tests/test_async_evaluator.py +137 -0
  39. agentegrity-0.2.0/tests/test_attestation.py +118 -0
  40. agentegrity-0.2.0/tests/test_cortical_llm.py +187 -0
  41. agentegrity-0.2.0/tests/test_evaluator.py +238 -0
  42. agentegrity-0.2.0/tests/test_monitor.py +124 -0
  43. agentegrity-0.2.0/tests/test_profile.py +98 -0
  44. agentegrity-0.2.0/tests/test_recovery.py +123 -0
@@ -0,0 +1,36 @@
1
+ # Python
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+ *.so
6
+ *.egg-info/
7
+ *.egg
8
+ dist/
9
+ build/
10
+ .eggs/
11
+
12
+ # Virtual environments
13
+ .venv/
14
+ venv/
15
+ env/
16
+
17
+ # IDE
18
+ .vscode/
19
+ .idea/
20
+ *.swp
21
+ *.swo
22
+ *~
23
+
24
+ # Testing
25
+ .pytest_cache/
26
+ .coverage
27
+ htmlcov/
28
+ .mypy_cache/
29
+
30
+ # OS
31
+ .DS_Store
32
+ Thumbs.db
33
+
34
+ # Distribution
35
+ *.whl
36
+ *.tar.gz
@@ -0,0 +1,189 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work.
38
+
39
+ "Derivative Works" shall mean any work, whether in Source or Object
40
+ form, that is based on (or derived from) the Work and for which the
41
+ editorial revisions, annotations, elaborations, or other modifications
42
+ represent, as a whole, an original work of authorship. For the purposes
43
+ of this License, Derivative Works shall not include works that remain
44
+ separable from, or merely link (or bind by name) to the interfaces of,
45
+ the Work and Derivative Works thereof.
46
+
47
+ "Contribution" shall mean any work of authorship, including
48
+ the original version of the Work and any modifications or additions
49
+ to that Work or Derivative Works thereof, that is intentionally
50
+ submitted to the Licensor for inclusion in the Work by the copyright owner
51
+ or by an individual or Legal Entity authorized to submit on behalf of
52
+ the copyright owner. For the purposes of this definition, "submitted"
53
+ means any form of electronic, verbal, or written communication sent
54
+ to the Licensor or its representatives, including but not limited to
55
+ communication on electronic mailing lists, source code control systems,
56
+ and issue tracking systems that are managed by, or on behalf of, the
57
+ Licensor for the purpose of discussing and improving the Work, but
58
+ excluding communication that is conspicuously marked or otherwise
59
+ designated in writing by the copyright owner as "Not a Contribution."
60
+
61
+ "Contributor" shall mean Licensor and any individual or Legal Entity
62
+ on behalf of whom a Contribution has been received by the Licensor and
63
+ subsequently incorporated within the Work.
64
+
65
+ 2. Grant of Copyright License. Subject to the terms and conditions of
66
+ this License, each Contributor hereby grants to You a perpetual,
67
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
68
+ copyright license to reproduce, prepare Derivative Works of,
69
+ publicly display, publicly perform, sublicense, and distribute the
70
+ Work and such Derivative Works in Source or Object form.
71
+
72
+ 3. Grant of Patent License. Subject to the terms and conditions of
73
+ this License, each Contributor hereby grants to You a perpetual,
74
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
75
+ (except as stated in this section) patent license to make, have made,
76
+ use, offer to sell, sell, import, and otherwise transfer the Work,
77
+ where such license applies only to those patent claims licensable
78
+ by such Contributor that are necessarily infringed by their
79
+ Contribution(s) alone or by combination of their Contribution(s)
80
+ with the Work to which such Contribution(s) was submitted. If You
81
+ institute patent litigation against any entity (including a
82
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
83
+ or a Contribution incorporated within the Work constitutes direct
84
+ or contributory patent infringement, then any patent licenses
85
+ granted to You under this License for that Work shall terminate
86
+ as of the date such litigation is filed.
87
+
88
+ 4. Redistribution. You may reproduce and distribute copies of the
89
+ Work or Derivative Works thereof in any medium, with or without
90
+ modifications, and in Source or Object form, provided that You
91
+ meet the following conditions:
92
+
93
+ (a) You must give any other recipients of the Work or
94
+ Derivative Works a copy of this License; and
95
+
96
+ (b) You must cause any modified files to carry prominent notices
97
+ stating that You changed the files; and
98
+
99
+ (c) You must retain, in the Source form of any Derivative Works
100
+ that You distribute, all copyright, patent, trademark, and
101
+ attribution notices from the Source form of the Work,
102
+ excluding those notices that do not pertain to any part of
103
+ the Derivative Works; and
104
+
105
+ (d) If the Work includes a "NOTICE" text file as part of its
106
+ distribution, then any Derivative Works that You distribute must
107
+ include a readable copy of the attribution notices contained
108
+ within such NOTICE file, excluding any notices that do not
109
+ pertain to any part of the Derivative Works, in at least one
110
+ of the following places: within a NOTICE text file distributed
111
+ as part of the Derivative Works; within the Source form or
112
+ documentation, if provided along with the Derivative Works; or,
113
+ within a display generated by the Derivative Works, if and
114
+ wherever such third-party notices normally appear. The contents
115
+ of the NOTICE file are for informational purposes only and
116
+ do not modify the License. You may add Your own attribution
117
+ notices within Derivative Works that You distribute, alongside
118
+ or as an addendum to the NOTICE text from the Work, provided
119
+ that such additional attribution notices cannot be construed
120
+ as modifying the License.
121
+
122
+ You may add Your own copyright statement to Your modifications and
123
+ may provide additional or different license terms and conditions
124
+ for use, reproduction, or distribution of Your modifications, or
125
+ for any such Derivative Works as a whole, provided Your use,
126
+ reproduction, and distribution of the Work otherwise complies with
127
+ the conditions stated in this License.
128
+
129
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
130
+ any Contribution intentionally submitted for inclusion in the Work
131
+ by You to the Licensor shall be under the terms and conditions of
132
+ this License, without any additional terms or conditions.
133
+ Notwithstanding the above, nothing herein shall supersede or modify
134
+ the terms of any separate license agreement you may have executed
135
+ with Licensor regarding such Contributions.
136
+
137
+ 6. Trademarks. This License does not grant permission to use the trade
138
+ names, trademarks, service marks, or product names of the Licensor,
139
+ except as required for reasonable and customary use in describing the
140
+ origin of the Work and reproducing the content of the NOTICE file.
141
+
142
+ 7. Disclaimer of Warranty. Unless required by applicable law or
143
+ agreed to in writing, Licensor provides the Work (and each
144
+ Contributor provides its Contributions) on an "AS IS" BASIS,
145
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
146
+ implied, including, without limitation, any warranties or conditions
147
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
148
+ PARTICULAR PURPOSE. You are solely responsible for determining the
149
+ appropriateness of using or redistributing the Work and assume any
150
+ risks associated with Your exercise of permissions under this License.
151
+
152
+ 8. Limitation of Liability. In no event and under no legal theory,
153
+ whether in tort (including negligence), contract, or otherwise,
154
+ unless required by applicable law (such as deliberate and grossly
155
+ negligent acts) or agreed to in writing, shall any Contributor be
156
+ liable to You for damages, including any direct, indirect, special,
157
+ incidental, or consequential damages of any character arising as a
158
+ result of this License or out of the use or inability to use the
159
+ Work (including but not limited to damages for loss of goodwill,
160
+ work stoppage, computer failure or malfunction, or any and all
161
+ other commercial damages or losses), even if such Contributor
162
+ has been advised of the possibility of such damages.
163
+
164
+ 9. Accepting Warranty or Additional Liability. While redistributing
165
+ the Work or Derivative Works thereof, You may choose to offer,
166
+ and charge a fee for, acceptance of support, warranty, indemnity,
167
+ or other liability obligations and/or rights consistent with this
168
+ License. However, in accepting such obligations, You may act only
169
+ on Your own behalf and on Your sole responsibility, not on behalf
170
+ of any other Contributor, and only if You agree to indemnify,
171
+ defend, and hold each Contributor harmless for any liability
172
+ incurred by, or claims asserted against, such Contributor by reason
173
+ of your accepting any such warranty or additional liability.
174
+
175
+ END OF TERMS AND CONDITIONS
176
+
177
+ Copyright 2026 Cogensec Research
178
+
179
+ Licensed under the Apache License, Version 2.0 (the "License");
180
+ you may not use this file except in compliance with the License.
181
+ You may obtain a copy of the License at
182
+
183
+ http://www.apache.org/licenses/LICENSE-2.0
184
+
185
+ Unless required by applicable law or agreed to in writing, software
186
+ distributed under the License is distributed on an "AS IS" BASIS,
187
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
188
+ See the License for the specific language governing permissions and
189
+ limitations under the License.
@@ -0,0 +1,132 @@
1
+ # The Agentegrity Manifesto
2
+
3
+ **Version 1.0 · March 2026**
4
+ **Cogensec Research**
5
+
6
+ ---
7
+
8
+ ## A New Word for a New Problem
9
+
10
+ We coined *agentegrity* because the problem it names did not have a word.
11
+
12
+ Autonomous AI agents reason, decide, act, and coordinate — often without human oversight, often across environments their designers never anticipated. The security industry responded with guardrails: filters on inputs, monitors on outputs, policies on tool access. These are necessary. They are not sufficient.
13
+
14
+ An agent can pass every guardrail check and still be compromised. Its reasoning can be manipulated without triggering input filters. Its memory can be poisoned without producing anomalous outputs. Its behavior can drift from specification so gradually that no monitoring threshold fires. The agent looks fine. The agent is not fine.
15
+
16
+ **Agentegrity** is the property of an AI agent being *whole* — maintaining consistent, verifiable, trustworthy operation across adversarial conditions, deployment environments, and time.
17
+
18
+ It is not a product. It is not a checklist. It is a measurable, enforceable, provable property of the agent itself.
19
+
20
+ ---
21
+
22
+ ## Definition
23
+
24
+ > **Agentegrity** (noun): The condition in which an autonomous AI agent maintains coherent reasoning, consistent behavior, and verifiable trustworthiness under adversarial pressure, across deployment contexts, and over time.
25
+ >
26
+ > An agent possesses agentegrity when three properties hold simultaneously:
27
+ > **adversarial coherence**, **environmental portability**, and **verifiable assurance**.
28
+
29
+ ---
30
+
31
+ ## The Three Properties
32
+
33
+ ### 1. Adversarial Coherence
34
+
35
+ An agent with adversarial coherence maintains consistent reasoning and decision-making under active attack. Its goals cannot be hijacked. Its reasoning chain cannot be silently redirected. Its outputs remain aligned with its specification even when its inputs, tools, memory, and peer agents are adversarially manipulated.
36
+
37
+ Adversarial coherence is not robustness in the ML sense — surviving perturbed inputs. It is *cognitive consistency* — the agent's internal reasoning process produces the same class of decisions regardless of adversarial interference in any channel: prompts, tool outputs, retrieved documents, inter-agent messages, or environmental signals.
38
+
39
+ **An agent without adversarial coherence can be turned against its operator without either party knowing.**
40
+
41
+ ### 2. Environmental Portability
42
+
43
+ An agent with environmental portability carries its integrity guarantees across deployment contexts. The same agent deployed in a cloud sandbox, at the edge, within a multi-agent swarm, or controlling a physical system maintains equivalent integrity properties — not identical implementations, but equivalent assurances.
44
+
45
+ This matters because agents are increasingly deployed across heterogeneous environments. An agent that is secure in a controlled cloud environment but exploitable when federated with untrusted peers, or when deployed on constrained edge hardware, does not possess integrity — it possesses *conditional* integrity, which is no integrity at all.
46
+
47
+ **An agent without environmental portability is only as secure as its weakest deployment.**
48
+
49
+ ### 3. Verifiable Assurance
50
+
51
+ An agent with verifiable assurance can *prove* its integrity state, not merely *claim* it. Integrity assessments produce cryptographic attestation records that are independently verifiable, tamper-evident, and auditable.
52
+
53
+ Observational security — "we watched the agent and it seemed fine" — is not assurance. Monitoring dashboards show what happened. Attestation records prove what the agent's state *was* at a specific point in time, signed in a way that cannot be retroactively altered.
54
+
55
+ **An agent without verifiable assurance asks you to trust it. An agent with verifiable assurance lets you verify it.**
56
+
57
+ ---
58
+
59
+ ## The Three Layers
60
+
61
+ Agentegrity is enforced through three architectural layers. Each layer addresses a different dimension of integrity. Together, they form a complete integrity envelope around the agent.
62
+
63
+ ### Adversarial Layer
64
+
65
+ The adversarial layer is the outermost defense. It continuously tests and validates the agent's resilience to attack. This is not a one-time penetration test — it is an ongoing, runtime evaluation of how the agent responds to adversarial pressure across all input channels.
66
+
67
+ Core functions:
68
+ - Attack surface enumeration and continuous mapping
69
+ - Real-time threat detection across prompt, tool, memory, and peer channels
70
+ - Adversarial coherence scoring against behavioral baselines
71
+ - Red team validation hooks for automated and manual testing
72
+ - Threat intelligence integration for emerging attack patterns
73
+
74
+ The adversarial layer answers: **can this agent be broken right now?**
75
+
76
+ ### Cortical Layer
77
+
78
+ The cortical layer monitors the agent's internal cognitive processes — the reasoning, memory, and decision-making that define what the agent *is*. Named for the cerebral cortex, the brain's executive processing center, this layer protects the higher-order functions that make an agent intelligent and make it dangerous when compromised.
79
+
80
+ Core functions:
81
+ - Reasoning chain integrity validation
82
+ - Memory provenance tracking and consistency verification
83
+ - Behavioral baseline maintenance and drift detection
84
+ - Cognitive conflict detection (contradictions between goals, instructions, memory, and actions)
85
+ - Internal state attestation and signing
86
+
87
+ The cortical layer answers: **is this agent still itself?**
88
+
89
+ ### Governance Layer
90
+
91
+ The governance layer enforces organizational policy, human oversight requirements, and compliance obligations. It is the bridge between the agent's technical integrity and the organizational context in which it operates.
92
+
93
+ Core functions:
94
+ - Policy-as-code enforcement with version control
95
+ - Human-in-the-loop escalation for high-risk decisions
96
+ - Compliance mapping to regulatory frameworks (NIST AI RMF, EU AI Act, ISO 42001)
97
+ - Immutable audit trail generation
98
+ - Break-glass emergency controls
99
+
100
+ The governance layer answers: **is this agent operating within authorized boundaries?**
101
+
102
+ ---
103
+
104
+ ## What Agentegrity Is Not
105
+
106
+ **Agentegrity is not guardrails.** Guardrails filter. Agentegrity evaluates the agent itself.
107
+
108
+ **Agentegrity is not monitoring.** Monitoring observes behavior. Agentegrity proves integrity state.
109
+
110
+ **Agentegrity is not alignment.** Alignment asks whether the agent's goals are good. Agentegrity asks whether the agent's goals are *intact*.
111
+
112
+ **Agentegrity is not a product.** It is a measurable property. Products can implement it. Frameworks can enforce it. Benchmarks can evaluate it. But no single vendor owns agentegrity any more than a single vendor owns "encryption."
113
+
114
+ ---
115
+
116
+ ## The Standard
117
+
118
+ This manifesto defines the concept. The [Agentegrity Framework Specification](spec/SPECIFICATION.md) defines the technical standard — how to measure the three properties, how to implement the three layers, what controls are required at each maturity level, and how to produce verifiable attestation records.
119
+
120
+ The specification is open. Implementations are welcome from any vendor, any framework, any deployment context. The integrity of autonomous agents is too important to be proprietary.
121
+
122
+ ---
123
+
124
+ ## Signatories
125
+
126
+ **Cogensec Research** — Originator and primary maintainer
127
+
128
+ We invite researchers, practitioners, and organizations building or deploying autonomous AI agents to adopt, implement, and extend the Agentegrity Framework.
129
+
130
+ ---
131
+
132
+ *Agentegrity is a coined term introduced by Cogensec Research in March 2026.*